© 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. 72278
    Prev
    Next
    INDEX
    Explanations

    fatal accident

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

    risks and potential challenges

    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
    л
    0.55
    Рис
    0.53
     Старки
    0.48
     হাইকমিশনার
    0.47
     anvil
    0.46
    язы
    0.46
     верх
    0.45
    assapi
    0.44
    ٢
    0.44
    DependentUpon
    0.44
    POSITIVE LOGITS
     Bic
    0.47
     entre
    0.46
     événement
    0.46
     nonprofit
    0.44
     istit
    0.43
     francisco
    0.42
     ഏത
    0.42
     sint
    0.41
     dr
    0.41
     φ
    0.41
    Activations Density 0.001%

    No Known Activations