© 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. 10-GEMMASCOPE-RES-131K
    7. 42883
    Prev
    Next
    INDEX
    Explanations

    fantasy, profound effect, exec(), wall crashing, TSX, Johnson &, Lords ruled

    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
     of
    -3.22
     to
    -1.74
     todėl
    -1.60
    {
    -1.56
     until
    -1.52
     einschließlich
    -1.51
    orithmic
    -1.46
     but
    -1.45
     situado
    -1.45
    नलोड
    -1.43
    POSITIVE LOGITS
     avena
    1.48
     turista
    1.46
     やすい
    1.45
     voda
    1.45
     trast
    1.45
    
    1.41
     siena
    1.39
     refroid
    1.38
     vada
    1.38
    くださった
    1.38
    Activations Density 0.030%

    No Known Activations