© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76683
    Prev
    Next
    INDEX
    Explanations

    warning messages

    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_34/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
     /\.(
    -0.82
    nadores
    -0.76
    quely
    -0.76
    回到了
    -0.75
     handy
    -0.74
     concierto
    -0.73
     örnek
    -0.73
    Très
    -0.73
     bearings
    -0.71
    居民
    -0.71
    POSITIVE LOGITS
    並不
    0.87
    雖
    0.77
    文獻
    0.75
    濫
    0.75
     fucking
    0.74
     chug
    0.73
    有時
    0.73
     創
    0.72
     basing
    0.72
    plante
    0.72
    Activations Density 0.030%

    No Known Activations