© 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. 2650
    Prev
    Next
    INDEX
    Explanations

    .ref, ::

    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
    ინ
    -0.84
     seats
    -0.71
     títulos
    -0.69
    関連項目
    -0.69
    ografía
    -0.69
    錬
    -0.68
     את
    -0.66
    넌
    -0.66
    입
    -0.65
    poda
    -0.65
    POSITIVE LOGITS
    カラオケ
    0.76
     anatomical
    0.70
     Failure
    0.70
    醫院
    0.68
     councillors
    0.66
     échou
    0.66
     عظ
    0.66
    主播
    0.66
    μει
    0.66
     citrus
    0.66
    Activations Density 0.057%

    No Known Activations