© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43575
    Prev
    Next
    INDEX
    Explanations

    information, evolution, resonance, connectivity, interaction

    np_acts-logits-general · gemini-2.5-flash-lite

    scientific terms related to energy transfer and resonance phenomena, particularly in physics, chemistry and spectroscopy.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires strongly on the names and acronyms of physical‐science phenomena or measurement methods (e.g. Overhauser effect, NOE, dipolar interactions, Förster resonance energy transfer, mutual information).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    蛧
    -1.68
    r
    -1.55
    t
    -1.48
     punya
    -1.47
    🔗
    -1.42
     даже
    -1.40
    เกง
    -1.37
     fisuras
    -1.36
    Permalink
    -1.36
     nawet
    -1.35
    POSITIVE LOGITS
    0
    1.52
     such
    1.52
    ogados
    1.52
    joso
    1.40
     evidentemente
    1.39
    bosky
    1.38
     sorprend
    1.37
     diminutive
    1.37
     between
    1.34
     hark
    1.34
    Activations Density 0.016%

    No Known Activations