© 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. 59868
    Prev
    Next
    INDEX
    Explanations

    take a

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

    about convenience, shiny, order

    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
    洴
    0.46
    utto
    0.45
    '<
    0.45
     validar
    0.45
    wellness
    0.43
     btw
    0.43
     valida
    0.43
    export
    0.42
    tarea
    0.42
    unum
    0.42
    POSITIVE LOGITS
     enhancement
    0.49
     ぞ
    0.46
    िकांत
    0.46
     تاک
    0.45
     contamination
    0.44
     penghargaan
    0.43
     Enhancement
    0.42
     encouragement
    0.41
     impregnation
    0.41
     inflexible
    0.41
    Activations Density 0.000%

    No Known Activations