© 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. 186669
    Prev
    Next
    INDEX
    Explanations

    i of ? _ yesterday

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

    repeatedly knocking, wheels, file, act

    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
     plateforme
    0.54
    뀌
    0.49
    뮤
    0.48
    ायत
    0.48
    گنڈ
    0.48
     данных
    0.47
    Gosudarstvennyj
    0.47
    امہ
    0.47
     данные
    0.47
     configurações
    0.46
    POSITIVE LOGITS
    i
    0.54
     of
    0.50
    ?,
    0.48
    _
    0.47
     yesterday
    0.47
     assort
    0.47
     Feeling
    0.46
     eligible
    0.46
     Yesterday
    0.46
    profit
    0.45
    Activations Density 0.000%

    No Known Activations