© 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. 2266
    Prev
    Next
    INDEX
    Explanations

    `cref="` and `doi:`

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

    module names and artifact IDs

    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
    bathing
    0.33
    🌌
    0.31
     行っ
    0.31
     raggiunto
    0.30
     scène
    0.29
     言っ
    0.29
    रिडोर
    0.29
    しよう
    0.29
     বলছেন
    0.29
    饗
    0.29
    POSITIVE LOGITS
     tov
    0.29
     B
    0.27
     T
    0.26
     kuti
    0.26
     P
    0.26
     "
    0.26
     total
    0.25
     constructive
    0.25
     לב
    0.25
    FundMe
    0.25
    Activations Density 0.001%

    No Known Activations