© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 127609
    Prev
    Next
    INDEX
    Explanations

    understand importance

    np_acts-logits-general · gemini-2.5-flash-lite

    asking direct questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ade
    0.46
    繁殖
    0.43
    россий
    0.43
    組合
    0.43
    矛
    0.42
    います
    0.41
    और
    0.40
    㚣
    0.40
    反映
    0.40
    Чтобы
    0.40
    POSITIVE LOGITS
    <unused61>
    0.47
     হাজির
    0.44
    Ã
    0.43
    could
    0.41
     δυνατό
    0.41
     Grill
    0.40
    even
    0.40
    lier
    0.39
    će
    0.39
     বেল
    0.39
    Activations Density 0.004%

    No Known Activations