© 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. 48367
    Prev
    Next
    INDEX
    Explanations

    numbers, phone numbers, identifiers

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

    # and number sequences

    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
    wal
    0.44
    лое
    0.43
    tiin
    0.41
    jour
    0.39
    rook
    0.39
    ல்ப
    0.39
    Ꮺ
    0.38
     ep
    0.37
    wrapperEl
    0.37
    rcl
    0.36
    POSITIVE LOGITS
     squeezing
    0.41
     Sinatra
    0.39
    早く
    0.37
    Stadium
    0.36
     могла
    0.35
     निकालते
    0.35
     मुंह
    0.35
     sinusoid
    0.35
     факуль
    0.35
    nobody
    0.35
    Activations Density 0.027%

    No Known Activations