© 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. 103675
    Prev
    Next
    INDEX
    Explanations

    code and lists

    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
    ي
    1.06
    ти
    1.04
    of
    1.02
    am
    0.96
    те
    0.95
    OF
    0.95
    ED
    0.95
    i
    0.93
    ON
    0.93
    EK
    0.90
    POSITIVE LOGITS
    larda
    0.93
    ies
    0.87
     scolded
    0.84
    ną
    0.81
     می‌کن
    0.80
     поверну
    0.80
     در
    0.79
    <0x8A>
    0.77
    <0xA5>
    0.77
    lop
    0.76
    Activations Density 0.014%

    No Known Activations