© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 111154
    Prev
    Next
    INDEX
    Explanations

    digging, understanding, and finding treasure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    נ
    0.54
    ט
    0.53
    ڎ
    0.53
    ב
    0.52
    饴
    0.52
    Jeśli
    0.52
    聁
    0.52
     contextos
    0.51
    ميم
    0.50
    إذا
    0.50
    POSITIVE LOGITS
     of
    0.51
     tunnel
    0.50
     (
    0.49
     solving
    0.48
    ;
    0.48
     -
    0.47
    ’
    0.47
     cleaning
    0.46
    t
    0.46
     measuring
    0.44
    Activations Density 0.006%

    No Known Activations