© 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. 16178
    Prev
    Next
    INDEX
    Explanations

    clear damage

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

    code, data, and concepts

    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
    どうぞ
    0.54
     잘못
    0.50
     принадлежа
    0.50
     βρίσκεται
    0.49
     Затем
    0.47
     Мор
    0.46
     ∈
    0.45
    āli
    0.45
     серви
    0.45
     Мон
    0.45
    POSITIVE LOGITS
    ("|
    0.46
     replaces
    0.42
    िकुलर
    0.42
    چھا
    0.41
     breezy
    0.41
    hesive
    0.41
    েন্দু
    0.40
    edent
    0.40
    NewUrlParser
    0.39
     noe
    0.39
    Activations Density 0.000%

    No Known Activations