© 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. 23371
    Prev
    Next
    INDEX
    Explanations

    numbered lists or dates

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

    chords (G), (F)

    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
     Бан
    0.45
    লিক
    0.44
    加速度
    0.44
     вікі
    0.42
    KeepOriginal
    0.41
    闿
    0.41
    Landing
    0.41
    丳
    0.40
     Söz
    0.40
    PlatformImage
    0.39
    POSITIVE LOGITS
    as
    0.53
     generally
    0.50
    $
    0.50
    into
    0.49
    upon
    0.49
    ro
    0.49
    esthesia
    0.47
    of
    0.46
    each
    0.46
     forfeit
    0.46
    Activations Density 0.001%

    No Known Activations