© 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. 248463
    Prev
    Next
    INDEX
    Explanations

    local at

    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
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.55
    ↵↵↵↵↵↵↵↵↵↵↵
    0.52
    ו
    0.50
    o
    0.50
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.50
     Huerta
    0.49
     prue
    0.48
     Galbraith
    0.48
     ನ
    0.47
     Mayer
    0.47
    POSITIVE LOGITS
    璘
    0.47
    ！（
    0.44
     photons
    0.43
    dons
    0.43
    did
    0.43
    春
    0.42
    AttrName
    0.42
     neutrino
    0.41
    匈
    0.41
    Feb
    0.40
    Activations Density 0.000%

    No Known Activations