© 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. 50456
    Prev
    Next
    INDEX
    Explanations

    root directory and variety of

    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
     Williamsburg
    -0.70
    buk
    -0.70
     نرم
    -0.69
     SERIAL
    -0.68
     attenuated
    -0.67
     Sachin
    -0.66
    جو
    -0.64
    setImage
    -0.64
    рено
    -0.64
     software
    -0.63
    POSITIVE LOGITS
     Calm
    0.75
    錫
    0.71
     spannend
    0.70
    TRAVIS
    0.67
    Calm
    0.66
     Lesson
    0.65
     induct
    0.65
    during
    0.65
     mộc
    0.64
    Cadastro
    0.64
    Activations Density 0.045%

    No Known Activations