© 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. 22-GEMMASCOPE-RES-131K
    7. 66847
    Prev
    Next
    INDEX
    Explanations

    Q and package starts

    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_22/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
     manualidades
    -1.27
     karty
    -1.21
     tirantes
    -1.17
     tornillo
    -1.16
     capucha
    -1.15
     playera
    -1.14
     autory
    -1.12
     lámparas
    -1.11
     Moscú
    -1.10
     décontract
    -1.10
    POSITIVE LOGITS
     his
    1.20
     in
    1.18
     he
    1.06
    1
    1.06
     out
    1.01
    9
    0.99
     other
    0.99
     at
    0.96
     with
    0.96
    or
    0.95
    Activations Density 0.000%

    No Known Activations