© 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. 72317
    Prev
    Next
    INDEX
    Explanations

    code selectors and expressions

    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
     ong
    -0.93
    🩱
    -0.88
    gación
    -0.87
    Ǜ
    -0.87
    picable
    -0.85
    assembled
    -0.85
    ΰ
    -0.83
    uisine
    -0.83
     XVIII
    -0.83
    ஸ்
    -0.82
    POSITIVE LOGITS
     lämp
    0.96
    ()=>{
    0.96
     oppressive
    0.88
     понять
    0.84
     Jenderal
    0.84
     anunciou
    0.84
     auprès
    0.83
    </h4>
    0.82
     kult
    0.82
     debió
    0.82
    Activations Density 0.029%

    No Known Activations