© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 34165
    Prev
    Next
    INDEX
    Explanations

    biological entities and processes

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

    This neuron detects technical or scientific terms related to biological and physical systems, particularly organisms, cells, proteins, and physical materials.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     feront
    -1.40
    romolecules
    -1.38
     It
    -1.31
    ionali
    -1.30
     disponibles
    -1.27
    谖
    -1.25
    悻
    -1.25
     magnifiques
    -1.23
    ของ
    -1.21
     jopa
    -1.21
    POSITIVE LOGITS
     activities
    1.32
    持つ
    1.30
     inherent
    1.29
     characteristics
    1.27
     whose
    1.23
     behavior
    1.20
     actions
    1.19
     mainly
    1.19
     own
    1.19
     use
    1.19
    Activations Density 0.227%

    No Known Activations