© 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. 93368
    Prev
    Next
    INDEX
    Explanations

    column, width, position

    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
     even
    -0.98
     then
    -0.96
     насос
    -0.82
    ({
    -0.81
     what
    -0.81
    ampu
    -0.81
    iclo
    -0.81
    atschapp
    -0.79
     first
    -0.77
     always
    -0.77
    POSITIVE LOGITS
    atized
    0.90
    zi
    0.88
     まで
    0.84
     dejo
    0.83
    看你
    0.83
     ments
    0.82
    ahora
    0.82
    obrázek
    0.80
    लाई
    0.80
     gla
    0.80
    Activations Density 0.003%

    No Known Activations