© 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. 228186
    Prev
    Next
    INDEX
    Explanations

    % cashfireplace

    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
     করিয়াছিল
    0.54
     করিলাম
    0.54
     হইতেছিল
    0.54
     করিয়াছে
    0.52
     করিয়াছি
    0.52
    ತೆಗೆ
    0.49
     rupam
    0.48
    婢
    0.47
    夊
    0.47
     रेत
    0.47
    POSITIVE LOGITS
    id
    0.57
    country
    0.54
    ↵↵
    0.52
    َن
    0.50
    y
    0.50
    EN
    0.49
    TIME
    0.46
    ing
    0.46
     ber
    0.45
     Cons
    0.44
    Activations Density 0.000%

    No Known Activations