© 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. 2727
    Prev
    Next
    INDEX
    Explanations

    month and day indicators

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

    dates and times

    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
    কীর
    0.45
    Nk
    0.45
    acağ
    0.43
    粔
    0.43
    獃
    0.42
    ້າງ
    0.42
    茈
    0.42
    鱻
    0.42
     বাঁধবেন
    0.42
     Akademii
    0.41
    POSITIVE LOGITS
    ./
    0.46
     ctrl
    0.42
     /
    0.41
     mins
    0.40
     communicative
    0.40
     MSG
    0.39
     [
    0.39
     expressive
    0.39
     २०२२
    0.39
     ワイド
    0.39
    Activations Density 0.058%

    No Known Activations