© 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. 74686
    Prev
    Next
    INDEX
    Explanations

    punctuation and mixed languages

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

    histogram, tools, list, car, whale

    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
     Plattform
    0.48
    )
    0.42
    )()
    0.42
    琀
    0.41
     tỏ
    0.39
    Json
    0.39
     wich
    0.39
     راست
    0.39
    গী
    0.39
    )";
    0.38
    POSITIVE LOGITS
    澳大利
    0.55
     SEASON
    0.51
    stalk
    0.50
     therapists
    0.49
    ಸ್ಯ
    0.49
    مع
    0.49
     представи
    0.49
     अनुभवी
    0.49
    雖然
    0.48
    શા
    0.48
    Activations Density 0.001%

    No Known Activations