© 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. 181253
    Prev
    Next
    INDEX
    Explanations

    DUI detection and cases

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

    predictions and forecasts

    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
    を生
    0.48
    نك
    0.47
    ذ
    0.46
    нде
    0.44
     longterm
    0.43
    ん
    0.43
    暦
    0.42
    سی
    0.42
    га
    0.42
    ну
    0.42
    POSITIVE LOGITS
    oki
    0.56
    oll
    0.52
    isions
    0.51
    raisal
    0.49
     আনুশকা
    0.49
    enak
    0.47
    ruption
    0.47
    olis
    0.46
    Cafe
    0.46
     নেয়
    0.46
    Activations Density 0.000%

    No Known Activations