© 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. 228442
    Prev
    Next
    INDEX
    Explanations

    timestamps

    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
    놁
    0.45
    ूती
    0.45
     BVHTree
    0.44
     একসাথে
    0.43
    茛
    0.43
     clockRadius
    0.42
     मिलकर
    0.41
     encuentran
    0.41
    ତି
    0.40
     mempert
    0.40
    POSITIVE LOGITS
    sp
    0.48
     soz
    0.48
    Y
    0.47
    학
    0.45
    AW
    0.44
    sync
    0.44
    swear
    0.44
    rem
    0.44
    reib
    0.44
    Maintenance
    0.44
    Activations Density 0.000%

    No Known Activations