© 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. 66945
    Prev
    Next
    INDEX
    Explanations

    service in

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

    lists of descriptive terms

    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
    reys
    0.52
    ri
    0.48
    5
    0.48
    Numbered
    0.48
    ite
    0.47
    rza
    0.47
    Las
    0.47
    ’
    0.47
    Tray
    0.46
     ACID
    0.46
    POSITIVE LOGITS
    ב
    0.52
     tecido
    0.52
     femei
    0.51
    дования
    0.50
    었고
    0.48
     bø
    0.48
    儩
    0.47
     segment
    0.47
    ברו
    0.47
     proto
    0.46
    Activations Density 0.000%

    No Known Activations