© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59584
    Prev
    Next
    INDEX
    Explanations

    copyright license usage

    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
     same
    -1.04
    ********/
    -0.96
     those
    -0.93
    έα
    -0.93
     ४
    -0.93
     it
    -0.92
    だったので
    -0.90
     dente
    -0.90
     bereits
    -0.90
    Смотрите
    -0.86
    POSITIVE LOGITS
     of
    1.48
     ceci
    1.02
    ICAL
    0.94
    鳕
    0.93
     themselves
    0.92
     statunit
    0.92
     aim
    0.91
    oluted
    0.90
    ensively
    0.89
     &
    0.88
    Activations Density 0.153%

    No Known Activations