© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 188882
    Prev
    Next
    INDEX
    Explanations

    AJ may dismiss

    np_acts-logits-general · gemini-2.5-flash-lite

    visually stunning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surfactant
    0.48
     hydroly
    0.47
     höch
    0.47
    说是
    0.47
    altung
    0.47
    鳖
    0.47
     sürü
    0.47
    hö
    0.46
     hyst
    0.46
     robber
    0.46
    POSITIVE LOGITS
    s
    0.47
    progress
    0.46
    untitled
    0.46
    progressive
    0.45
     for
    0.45
    morph
    0.45
    uza
    0.44
    originals
    0.43
     obtainable
    0.43
    =?";
    0.43
    Activations Density 0.000%

    No Known Activations