© 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. 113488
    Prev
    Next
    INDEX
    Explanations

    numbers and counts

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

    disc, 2, filters, premises

    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
     আজও
    0.48
     cultivate
    0.47
     rethink
    0.47
     sông
    0.46
    ارہ
    0.46
    regulate
    0.46
    ёр
    0.46
    <unused50>
    0.46
     أساس
    0.45
    ूटूथ
    0.45
    POSITIVE LOGITS
     in
    0.51
    ;
    0.50
    да
    0.49
    (
    0.48
    arten
    0.47
    0.47
    ];
    0.47
    he
    0.47
    します
    0.46
    0.46
    Activations Density 0.000%

    No Known Activations