© 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. 137557
    Prev
    Next
    INDEX
    Explanations

    caused by, blow up, steal big

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

    connections, descriptions, or states

    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
    чений
    0.52
     નિય
    0.50
    駭
    0.48
    жий
    0.47
    ຽ
    0.46
    נה
    0.46
    ница
    0.46
    ба
    0.46
    ках
    0.46
    ិត
    0.45
    POSITIVE LOGITS
     p
    0.51
     pojawi
    0.49
     sparen
    0.47
     pat
    0.47
    OS
    0.46
     cały
    0.46
     lider
    0.46
     parentheses
    0.46
    rescences
    0.46
    Heroes
    0.45
    Activations Density 0.000%

    No Known Activations