© 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. 16-GEMMASCOPE-2-RES-262K
    7. 41871
    Prev
    Next
    INDEX
    Explanations

    name, string, cars

    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_16_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
    leri
    0.73
     bullpen
    0.73
    dır
    0.71
     colloquial
    0.69
     אחד
    0.68
    -
    0.68
    atu
    0.67
     quadrant
    0.67
     cordial
    0.67
    oin
    0.66
    POSITIVE LOGITS
    ز
    1.14
    ח
    1.10
    غ
    1.04
    ب
    1.00
    ى
    1.00
    ون
    0.97
    مر
    0.95
    ξ
    0.95
    ρ
    0.95
    ر
    0.94
    Activations Density 0.002%

    No Known Activations