© 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. 34-GEMMASCOPE-RES-131K
    7. 58607
    Prev
    Next
    INDEX
    Explanations

    AWS role, Optical modulators, Short-chain, Play Store

    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
    %
    -1.01
     %
    -0.79
    generally
    -0.77
    )}(\
    -0.72
    pended
    -0.72
     bán
    -0.72
    (...
    -0.71
    Presidential
    -0.71
     perpé
    -0.71
     %(
    -0.71
    POSITIVE LOGITS
    üttel
    0.78
    )';
    0.77
     Interpreter
    0.76
    霈
    0.74
    cipe
    0.73
    SizeMode
    0.73
    ньому
    0.72
    ATORY
    0.71
     Elbow
    0.71
    ژه
    0.71
    Activations Density 0.015%

    No Known Activations