© 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. 69201
    Prev
    Next
    INDEX
    Explanations

    foreign language and grammar structures

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

    books and multilingual phrases

    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
    avu
    0.49
     بازیکن
    0.49
    mp
    0.47
    怨
    0.46
    punt
    0.46
    プレイヤー
    0.45
    aut
    0.45
    ῆ
    0.45
    킁
    0.45
    idname
    0.44
    POSITIVE LOGITS
     dau
    0.54
     ChAT
    0.54
     Konz
    0.52
     bagaimana
    0.51
    t
    0.51
     Wiel
    0.51
     Naf
    0.48
     Dij
    0.48
     положение
    0.48
     Nicol
    0.47
    Activations Density 0.001%

    No Known Activations