© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 83651
    Prev
    Next
    INDEX
    Explanations

    non-

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

    speech, translation, C++

    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
    讨厌
    0.48
     unlawfully
    0.46
    进步
    0.43
    argu
    0.43
    빤
    0.43
     자신의
    0.42
    ეგ
    0.41
     месяца
    0.41
     breastfeeding
    0.41
    が好き
    0.40
    POSITIVE LOGITS
    ()}
    0.45
     NON
    0.44
    construction
    0.41
     phosphoric
    0.40
    遴
    0.40
     regularization
    0.40
    setminus
    0.40
    )};
    0.40
     internals
    0.40
     non
    0.39
    Activations Density 0.001%

    No Known Activations