© 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. 22-GEMMASCOPE-RES-131K
    7. 130288
    Prev
    Next
    INDEX
    Explanations

    inhibitory and suppressive actions

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

    This neuron detects verbs that describe inhibition or suppression of biological processes, such as "inhibits," "suppresses," "impairs," "attenuates," and "blocks."

    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
    蛱
    -1.74
    eſ
    -1.55
    
    -1.50
     ſol
    -1.47
    撄
    -1.45
     dépasser
    -1.44
    ឪ
    -1.40
     dvě
    -1.40
    ſi
    -1.39
    illance
    -1.38
    POSITIVE LOGITS
     in
    2.38
     both
    2.14
     not
    2.00
     all
    1.98
     various
    1.68
     only
    1.64
     very
    1.64
     just
    1.63
     or
    1.59
     diverse
    1.52
    Activations Density 0.259%

    No Known Activations