© 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. 60238
    Prev
    Next
    INDEX
    Explanations

    lists and comparisons

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

    continuous learning

    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
     подроб
    0.50
    kring
    0.47
     octave
    0.47
    ber
    0.45
    르
    0.45
    как
    0.44
    bered
    0.44
    闇
    0.43
    chaos
    0.43
    riors
    0.43
    POSITIVE LOGITS
     najbli
    0.63
     fisi
    0.50
     söz
    0.48
     tế
    0.47
     Jno
    0.47
    erView
    0.46
    LoggedIn
    0.46
     wewnętr
    0.45
     convid
    0.44
     mộ
    0.44
    Activations Density 0.000%

    No Known Activations