© 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. 40091
    Prev
    Next
    INDEX
    Explanations

    reduced paperwork, costs, consumption

    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
    ar
    0.49
    res
    0.48
    R
    0.47
    le
    0.46
    built
    0.43
    チャ
    0.43
     evitar
    0.43
    ous
    0.43
    antiene
    0.43
    re
    0.42
    POSITIVE LOGITS
    <unused2175>
    0.48
    জিৎ
    0.47
    鲔
    0.46
    testAvg
    0.46
     மேலே
    0.45
    dSample
    0.45
     Liquids
    0.43
     ግራም
    0.41
     বছ
    0.41
     martyrdom
    0.39
    Activations Density 0.002%

    No Known Activations