© 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. 220077
    Prev
    Next
    INDEX
    Explanations

    indications and requests

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

    maintain, version, organize

    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
    pots
    0.44
     interag
    0.43
    ION
    0.42
     //}
    0.42
    ತರ
    0.41
     criminality
    0.41
     BasicContainer
    0.41
    Gson
    0.41
    BeerItem
    0.41
    Fate
    0.41
    POSITIVE LOGITS
     طل
    0.53
     नमू
    0.53
     enfri
    0.53
     купи
    0.48
     indicaciones
    0.48
     অনুরোধ
    0.48
    冷却
    0.48
     Gutiérrez
    0.48
    尭
    0.48
     ඔහුගේ
    0.48
    Activations Density 0.000%

    No Known Activations