© 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. 19384
    Prev
    Next
    INDEX
    Explanations

    ideal candidate

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

    ideal candidate

    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
    ด
    0.70
    さ
    0.68
    د
    0.59
    ד
    0.57
    ara
    0.57
    再加上
    0.55
    ות
    0.54
    ระดับ
    0.54
    ኤ
    0.53
    ти
    0.53
    POSITIVE LOGITS
    Ideal
    0.95
     Ideal
    0.92
     идеа
    0.79
     ideales
    0.77
    ideal
    0.73
    ка
    0.71
    Ide
    0.71
     idéal
    0.71
     ideals
    0.70
    理想
    0.70
    Activations Density 0.019%

    No Known Activations