© 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. 2566
    Prev
    Next
    INDEX
    Explanations

    code and module imports

    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
    Ở
    -0.77
    lidae
    -0.76
    iliares
    -0.76
    Egg
    -0.72
     conveyance
    -0.68
    CHAR
    -0.68
    道理
    -0.66
     бухгал
    -0.66
    veien
    -0.66
     gawas
    -0.66
    POSITIVE LOGITS
    jardin
    0.73
    velu
    0.73
    onavirus
    0.72
    isance
    0.72
    Declared
    0.71
     Thur
    0.70
    joba
    0.70
     Judd
    0.69
    casm
    0.69
     JUD
    0.68
    Activations Density 0.036%

    No Known Activations