© 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. 153879
    Prev
    Next
    INDEX
    Explanations

    follow, please, anything, these

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

    dinner at, dangers of, good projects

    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
    BeerItem
    0.48
     Decedent
    0.48
    🧂
    0.48
    აცი
    0.47
    зів
    0.46
     BOARDSIZE
    0.46
    ꔰ
    0.45
     strListName
    0.45
    会員
    0.44
    <unused2113>
    0.44
    POSITIVE LOGITS
    y
    0.56
    v
    0.54
    id
    0.52
    up
    0.51
    guid
    0.51
    kl
    0.51
    ia
    0.50
    comprom
    0.50
    ched
    0.50
    unters
    0.50
    Activations Density 0.000%

    No Known Activations