© 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. 21327
    Prev
    Next
    INDEX
    Explanations

    earlier

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

    final answer predictions

    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
    ჰ
    0.42
    立った
    0.41
     그대로
    0.41
     ഓര്‍
    0.41
    FieldName
    0.40
    RO
    0.40
    NODE
    0.40
    ushed
    0.40
    FILTER
    0.40
    *-
    0.40
    POSITIVE LOGITS
    يتي
    0.46
    ář
    0.42
     Manhattan
    0.41
    我在
    0.40
    ↵
    0.39
    azioni
    0.39
     Max
    0.39
     Wilkinson
    0.38
     created
    0.38
    iture
    0.38
    Activations Density 0.001%

    No Known Activations