© 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. 13943
    Prev
    Next
    INDEX
    Explanations

    active and related states

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

    This neuron fires on tokens containing the root sequence “activ” (e.g. active, actively, activation, activated, and equivalent forms in other languages).

    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
    '
    -2.30
     that
    -2.27
    ↵
    -2.00
     ´
    -1.85
     arbol
    -1.78
     locally
    -1.69
    种植
    -1.66
     itſelf
    -1.65
    hhh
    -1.64
     緑
    -1.64
    POSITIVE LOGITS
    ﾈ
    2.30
    );
    2.14
    他的
    2.11
     That
    2.09
    
    2.08
    ｧ
    2.06
     Даже
    2.03
    ());
    2.03
     minha
    2.00
     Когда
    1.99
    Activations Density 0.006%

    No Known Activations