© 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. 241383
    Prev
    Next
    INDEX
    Explanations

    take out

    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
    К
    0.48
    િ
    0.48
    譚
    0.46
    িল্প
    0.44
    Кла
    0.43
    Κ
    0.42
    ாட
    0.42
    Е
    0.42
    t
    0.42
    কর
    0.42
    POSITIVE LOGITS
     بنابراین
    0.53
     숫자
    0.49
    ancake
    0.46
     견
    0.45
     aliqua
    0.43
     스스로
    0.43
     وجہ
    0.43
    ậ
    0.42
     ایک
    0.42
     coolant
    0.42
    Activations Density 0.000%

    No Known Activations