© 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. 17575
    Prev
    Next
    INDEX
    Explanations

    percentages and accuracy

    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
    ğ
    0.52
    \
    0.51
    &
    0.50
     tint
    0.49
    ى
    0.48
    ur
    0.47
    enl
    0.46
    k
    0.44
    Burn
    0.44
    ></
    0.43
    POSITIVE LOGITS
    ੱਚ
    0.51
    Ἄ
    0.50
     רו
    0.49
    ಟ್‌
    0.49
     ਤੁਹਾ
    0.49
    <unused297>
    0.49
    <unused2213>
    0.49
     মেড
    0.48
    ਮ
    0.48
    ೪
    0.47
    Activations Density 0.000%

    No Known Activations