© 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. 97713
    Prev
    Next
    INDEX
    Explanations

    concepts on, form and, target protein

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

    adding skills and concepts

    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
    '
    0.66
    .
    0.63
     ¨
    0.59
     Kevin
    0.59
    t
    0.59
    c
    0.59
      
    0.58
     Den
    0.57
     D
    0.57
     This
    0.57
    POSITIVE LOGITS
    ნება
    0.50
     వీరి
    0.49
    myButtons
    0.49
    诤
    0.49
    QAry
    0.48
    ángulos
    0.48
    strateg
    0.48
     ორგანო
    0.48
    <unused53>
    0.47
    叁章
    0.47
    Activations Density 0.000%

    No Known Activations