© 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. 32758
    Prev
    Next
    INDEX
    Explanations

    without warranties

    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
     беспла
    -0.85
    free
    -0.77
    ềm
    -0.76
    FREE
    -0.76
     free
    -0.75
     varandra
    -0.73
     POLICY
    -0.72
    Số
    -0.71
    Blanco
    -0.70
    Free
    -0.69
    POSITIVE LOGITS
    цька
    0.68
     ન
    0.67
    Ｃ
    0.66
    MOUTH
    0.64
     riso
    0.63
     DLL
    0.63
    rä
    0.63
     التي
    0.63
    Pautan
    0.62
    大野
    0.62
    Activations Density 0.113%

    No Known Activations