© 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. 10-GEMMASCOPE-RES-131K
    7. 103065
    Prev
    Next
    INDEX
    Explanations

    take, grab, or steal

    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_10/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
     in
    -2.55
     to
    -2.22
     by
    -2.20
     or
    -2.19
     at
    -2.05
     as
    -2.02
     you
    -2.00
     out
    -2.00
     on
    -1.95
    It
    -1.93
    POSITIVE LOGITS
    냑
    2.36
     semelh
    2.22
     pérd
    2.03
     drenaje
    2.03
    izacja
    1.98
    糁
    1.95
     probabilmente
    1.94
    así
    1.94
     Infór
    1.93
    읗
    1.90
    Activations Density 0.018%

    No Known Activations