© 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. 31462
    Prev
    Next
    INDEX
    Explanations

    code segments, data, licensed content

    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
     アルバム
    -0.78
     Voulez
    -0.77
     BIBLIO
    -0.69
    𝒰
    -0.69
     poodle
    -0.68
     добраться
    -0.66
     emoticon
    -0.66
     alde
    -0.66
     cang
    -0.66
     WRITER
    -0.65
    POSITIVE LOGITS
    kse
    0.71
    inha
    0.70
     Bou
    0.67
     نوفمبر
    0.67
    illot
    0.67
     Leib
    0.66
     Builder
    0.66
    Cran
    0.66
    inin
    0.65
    Bou
    0.65
    Activations Density 0.092%

    No Known Activations