© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110713
    Prev
    Next
    INDEX
    Explanations

    names starting with J, Jod, Yol

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Avion
    -0.90
    NQ
    -0.81
    اوم
    -0.78
    alek
    -0.78
    hooting
    -0.77
     Baptiste
    -0.77
    blik
    -0.76
    kst
    -0.75
     splitter
    -0.75
    BM
    -0.74
    POSITIVE LOGITS
    کوراسیون
    0.74
    Kdo
    0.71
    wurde
    0.70
     estimated
    0.69
    favor
    0.68
    transfers
    0.68
    Cursos
    0.68
     successfully
    0.68
     المط
    0.68
    サンタ
    0.67
    Activations Density 0.026%

    No Known Activations