© 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-16K
    7. 12676
    Prev
    Next
    INDEX
    Explanations

    statement

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

    exceptions: FileNotFoundError, ValueError

    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_16k_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
    تبار
    0.45
    Biscuit
    0.44
    თა
    0.43
     statutes
    0.40
    땃
    0.39
    ನಿಯ
    0.39
    Mur
    0.39
     Actin
    0.39
     salami
    0.38
    നായി
    0.38
    POSITIVE LOGITS
    io
    0.48
     छोटे
    0.46
     일으
    0.45
     सकता
    0.44
     ảnh
    0.44
     propia
    0.43
     रायपुर
    0.43
    ios
    0.42
     初始化
    0.42
    र
    0.42
    Activations Density 0.170%

    No Known Activations