© 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. 233204
    Prev
    Next
    INDEX
    Explanations

    foreign languages and HTML tags

    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
     ಸಾಕ
    0.51
     pyruvate
    0.50
    মিনা
    0.48
     결국
    0.47
     архіви
    0.46
    今の
    0.46
    栦
    0.46
     यौन
    0.45
     भिख
    0.44
    我现在
    0.44
    POSITIVE LOGITS
    dır
    0.50
    <h4>
    0.49
     háb
    0.48
    وهات
    0.47
    a
    0.46
    ́s
    0.45
     These
    0.45
     Ön
    0.45
    ترك
    0.45
     adlı
    0.45
    Activations Density 0.001%

    No Known Activations