© 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. 8188
    Prev
    Next
    INDEX
    Explanations

    prefixes followed by specific tokens

    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
    );
    -1.98
     and
    -1.94
    t
    -1.88
    孓
    -1.55
    ()",
    -1.53
     doméstico
    -1.52
     XXXIV
    -1.52
     زیرا
    -1.51
     LABORATOR
    -1.51
     waaronder
    -1.49
    POSITIVE LOGITS
    轳
    1.79
     Vielen
    1.65
     ulei
    1.61
    </em>
    1.60
     recommandé
    1.59
    inston
    1.58
    embang
    1.55
    Seems
    1.53
    lgari
    1.52
     conseillé
    1.50
    Activations Density 0.000%

    No Known Activations