© 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. 10-GEMMASCOPE-RES-131K
    7. 59759
    Prev
    Next
    INDEX
    Explanations

    inhibition, inhibitors, inhibitory

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

    terms related to inhibition or inhibitory activity in scientific/medical 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_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
     a
    -1.72
     probably
    -1.63
    (
    -1.61
    ៚
    -1.59
     had
    -1.59
     Probably
    -1.57
     sogar
    -1.56
     nocturna
    -1.55
     coreana
    -1.55
     Apparently
    -1.53
    POSITIVE LOGITS
    }$
    1.73
     レース
    1.69
    ).
    1.63
     biet
    1.63
    ೢ
    1.63
    檍
    1.61
    耵
    1.61
     against
    1.58
    ），
    1.57
    \_
    1.55
    Activations Density 0.180%

    No Known Activations