© 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. 128703
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly fires on the literal token “give.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    describe how

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Explicación
    -0.75
     converti
    -0.74
    把自己
    -0.74
     المكان
    -0.73
     требует
    -0.71
    メルカリ
    -0.71
    的で
    -0.71
     coscienza
    -0.71
    なのでしょう
    -0.71
    INDICE
    -0.71
    POSITIVE LOGITS
    ikations
    0.96
    BOTTOM
    0.93
     müßte
    0.83
    փ
    0.79
     рису
    0.78
    hazardous
    0.77
    mittag
    0.77
     NgModule
    0.77
    harapkan
    0.77
     inicialmente
    0.76
    Activations Density 0.062%

    No Known Activations