© 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. 40-GEMMASCOPE-2-RES-262K
    7. 31733
    Prev
    Next
    INDEX
    Explanations

    numbers and measures

    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_40_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
    والي
    0.54
     longitudine
    0.53
    ಷ
    0.53
    ouvrage
    0.52
    ያን
    0.51
     pretensions
    0.50
    कों
    0.50
     Δη
    0.49
    وال
    0.48
    ફેદ
    0.48
    POSITIVE LOGITS
    0
    0.59
    *
    0.53
    <0x80>
    0.52
    '
    0.50
    ak
    0.46
    za
    0.46
    yst
    0.44
    eras
    0.44
    \
    0.42
    iz
    0.42
    Activations Density 0.028%

    No Known Activations