© 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. 41047
    Prev
    Next
    INDEX
    Explanations

    scientific groups and substances

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

    terms related to scientific and technical groups, products, processes, or programs.

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

    This neuron fires on multi‐syllable, domain‐specific technical terms (e.g. specialized scientific nouns).

    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
    的
    -1.73
    埽
    -1.52
    の
    -1.44
     ۱۲
    -1.39
    及
    -1.34
    joyed
    -1.34
    omato
    -1.34
    镦
    -1.33
    гда
    -1.32
    Obtener
    -1.32
    POSITIVE LOGITS
     verletzt
    1.47
     überzeugt
    1.39
     It
    1.34
     \
    1.34
     verdadera
    1.34
     This
    1.29
     contemplating
    1.28
     besonderes
    1.28
     We
    1.27
     In
    1.26
    Activations Density 0.333%

    No Known Activations