© 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. 117780
    Prev
    Next
    INDEX
    Explanations

    J. and names

    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
    nets
    -0.81
    xes
    -0.73
    言語
    -0.71
    発信
    -0.70
    adra
    -0.69
     fwd
    -0.69
     Unic
    -0.68
    theria
    -0.68
     authors
    -0.67
    sional
    -0.67
    POSITIVE LOGITS
     Selb
    0.75
    iconductor
    0.73
    隐
    0.67
    אַ
    0.66
     abreast
    0.66
     bénéfic
    0.66
    の一
    0.65
     nám
    0.65
    Contour
    0.65
    fraud
    0.64
    Activations Density 0.015%

    No Known Activations