© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 123383
    Prev
    Next
    INDEX
    Explanations

    articles, numbers, justification, or history

    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
    Z
    0.59
    ب
    0.59
    B
    0.57
    O
    0.57
    Ş
    0.51
    I
    0.47
    Ņ
    0.47
     মাধ্যমিক
    0.47
    s
    0.45
    C
    0.45
    POSITIVE LOGITS
     verändert
    0.53
     obt
    0.46
     gleiche
    0.46
    ുടെ
    0.43
     അയാൾ
    0.43
     തന്നെ
    0.43
     své
    0.43
    يته
    0.42
     sigur
    0.42
     ครอง
    0.42
    Activations Density 0.000%

    No Known Activations