© 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. 239561
    Prev
    Next
    INDEX
    Explanations

    continues or repeats

    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
    ），
    0.52
    》，
    0.47
    ").
    0.46
     מב
    0.46
    stech
    0.46
    sections
    0.45
    )$,
    0.45
    n
    0.45
    "),
    0.44
    overty
    0.44
    POSITIVE LOGITS
     erneut
    0.59
     fortfarande
    0.58
     weiterhin
    0.56
     nieuwe
    0.55
     opnieuw
    0.53
     முயற்
    0.53
     intenta
    0.52
     deseja
    0.52
     frisch
    0.52
     unul
    0.50
    Activations Density 0.002%

    No Known Activations