© 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. 39520
    Prev
    Next
    INDEX
    Explanations

    foreign words and technical terms

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

    technical and multilingual keywords

    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
    in
    0.62
    ur
    0.50
    il
    0.50
    i
    0.49
    m
    0.48
    ie
    0.46
    y
    0.45
    dra
    0.44
    í
    0.44
    is
    0.44
    POSITIVE LOGITS
     けど
    0.50
    પ્ર
    0.49
     fscanf
    0.46
    র্জাতিক
    0.44
     inscreva
    0.43
    Бы
    0.43
     qDebug
    0.42
    ិច្
    0.42
     interrogate
    0.41
    жений
    0.41
    Activations Density 0.000%

    No Known Activations