© 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. 66112
    Prev
    Next
    INDEX
    Explanations

    conditions, entities, and states

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

    basic concepts and technical jargon

    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
    扬
    0.49
    ärg
    0.49
    ﹚
    0.46
    。
    0.46
    俏
    0.45
    长
    0.43
     җиңү
    0.42
    踌
    0.42
     의견
    0.42
    牵
    0.42
    POSITIVE LOGITS
     ও
    0.51
     আজকে
    0.47
     ಹಾಗೂ
    0.47
     ഉള്ള
    0.46
     ಅದ
    0.46
     hago
    0.46
     illiterate
    0.46
     AppException
    0.45
     Jharkhand
    0.45
    splitted
    0.45
    Activations Density 0.000%

    No Known Activations