© 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. 137526
    Prev
    Next
    INDEX
    Explanations

    time-based sequences and events

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

    non-public information

    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
     животных
    0.49
    یع
    0.46
    डोर
    0.45
     международных
    0.45
    แหน
    0.44
    Cookies
    0.44
    पोस्ट
    0.44
    纣
    0.43
    ธุ
    0.42
    ルトラ
    0.42
    POSITIVE LOGITS
    ើត
    0.50
    uš
    0.48
    該
    0.48
    re
    0.47
     Goto
    0.46
     নয়া
    0.46
    gcj
    0.46
    ué
    0.46
    цією
    0.45
     CET
    0.45
    Activations Density 0.000%

    No Known Activations