© 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. 72462
    Prev
    Next
    INDEX
    Explanations

    you have to

    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_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
     need
    -1.96
    ↵
    -1.66
    1
    -1.63
     should
    -1.58
    ↵↵
    -1.51
    3
    -1.50
    <b>
    -1.49
     have
    -1.47
     can
    -1.43
    6
    -1.43
    POSITIVE LOGITS
    嘞
    1.82
    aktivi
    1.62
     cinturón
    1.57
    ₂+
    1.56
     绒
    1.55
     kreatif
    1.55
     célè
    1.52
    üşonlu
    1.48
     ejemplar
    1.48
    providedIn
    1.48
    Activations Density 0.030%

    No Known Activations