© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72209
    Prev
    Next
    INDEX
    Explanations

    measuring health and progress

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

    This neuron activates for verbs related to measuring, quantifying, or assessing, particularly in scientific contexts.

    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
     meinem
    -1.41
     keinem
    -1.30
     একটি
    -1.30
    很多的
    -1.29
     irgende
    -1.28
    已经是
    -1.25
     Ihrem
    -1.23
    vey
    -1.17
    quot
    -1.16
     trotzdem
    -1.16
    POSITIVE LOGITS
     how
    2.70
     whether
    1.97
     what
    1.73
     where
    1.66
     the
    1.55
     changes
    1.52
     which
    1.48
     who
    1.38
     just
    1.38
    bióticos
    1.31
    Activations Density 0.195%

    No Known Activations