© 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. 184493
    Prev
    Next
    INDEX
    Explanations

    video, table, purchased, needed, Deck

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

    retrieval and analysis

    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
     as
    0.42
     review
    0.42
     safety
    0.42
    %
    0.41
     career
    0.40
    _
    0.40
     unisex
    0.40
    REVIEW
    0.39
    ینگ
    0.39
    ”]
    0.38
    POSITIVE LOGITS
    yai
    0.60
     drugih
    0.55
     adhipp
    0.54
     ジョ
    0.53
     सूत्रकृ
    0.52
    itabbo
    0.52
     бас
    0.51
     namik
    0.51
     бумаги
    0.51
     функ
    0.50
    Activations Density 0.001%

    No Known Activations