© 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. 84709
    Prev
    Next
    INDEX
    Explanations

    Tyre sole

    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
     навіть
    0.43
    ﾓ
    0.41
    KW
    0.41
     disob
    0.41
    ↵
    0.40
     حتی
    0.40
    ່ມ
    0.40
    DS
    0.39
     complète
    0.39
     sana
    0.39
    POSITIVE LOGITS
    وم
    0.50
     Labrenzia
    0.43
    地产
    0.41
    균
    0.41
    緩
    0.40
    玉米
    0.40
    葶
    0.40
    ت
    0.39
    ോക
    0.39
    嵓
    0.39
    Activations Density 0.002%

    No Known Activations