© 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. 22-GEMMASCOPE-RES-131K
    7. 33643
    Prev
    Next
    INDEX
    Explanations

    U.S. patents

    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
    =='
    -1.16
     (
    -1.09
     methods
    -0.94
    !='
    -0.93
     are
    -0.93
    ://"
    -0.92
    cxx
    -0.90
     '
    -0.90
     doctrine
    -0.89
     technik
    -0.89
    POSITIVE LOGITS
     取り付け
    1.13
     représentants
    1.04
    vgili
    1.00
     новую
    0.96
     pieni
    0.96
    żs
    0.96
    Sonntag
    0.95
     entw
    0.93
     utilizza
    0.93
    帖最后由
    0.93
    Activations Density 0.001%

    No Known Activations