© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92853
    Prev
    Next
    INDEX
    Explanations

    setting colors with values

    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
    cakes
    -0.75
    Раз
    -0.71
     Font
    -0.70
    قاء
    -0.68
     щоб
    -0.68
     чтобы
    -0.68
    black
    -0.68
     Profits
    -0.67
     NLP
    -0.67
     predstav
    -0.66
    POSITIVE LOGITS
     которому
    0.78
    alanx
    0.73
    なもの
    0.73
    ካ
    0.71
     peduli
    0.71
    ENCIAS
    0.71
    astronomie
    0.70
     útil
    0.70
    rophilic
    0.69
     summation
    0.69
    Activations Density 0.058%

    No Known Activations