© 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. 23298
    Prev
    Next
    INDEX
    Explanations

    self control, bureau chief

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

    different styles, kinds, genres

    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
    Images
    0.48
    Ago
    0.41
    Pics
    0.40
    I
    0.40
    Puzzle
    0.39
    Means
    0.39
    cabinet
    0.39
    弱
    0.39
    i
    0.38
    ｼ
    0.38
    POSITIVE LOGITS
     Tatra
    0.54
     Sval
    0.54
     každ
    0.52
     Leop
    0.52
     katth
    0.52
     Nederlands
    0.51
     বাড়ি
    0.51
     केलं
    0.51
    igné
    0.50
     zwier
    0.50
    Activations Density 0.000%

    No Known Activations