© 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. 128417
    Prev
    Next
    INDEX
    Explanations

    html meta tags

    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
    していない
    -0.87
     name
    -0.87
     pointed
    -0.85
     pointing
    -0.84
     اهم
    -0.82
     ваших
    -0.80
    anging
    -0.80
    ｂ
    -0.79
     aflu
    -0.78
     affords
    -0.77
    POSITIVE LOGITS
     ľudí
    0.79
    jectories
    0.78
     stedet
    0.78
    bottomrule
    0.77
    sprechend
    0.76
     ženy
    0.75
    vereign
    0.75
     EBITDA
    0.74
     borehole
    0.73
     légales
    0.72
    Activations Density 0.020%

    No Known Activations