© 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. 128172
    Prev
    Next
    INDEX
    Explanations

    program requirement

    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
     to
    -1.27
     создавать
    -1.11
    家は
    -1.08
     its
    -1.05
     boya
    -1.02
    jScrollPane
    -1.02
     inconveniente
    -1.00
     esporte
    -0.99
     prípade
    -0.99
    tev
    -0.98
    POSITIVE LOGITS
    ⌀
    0.99
    sgn
    0.99
     infatti
    0.98
    땐
    0.98
     skrevet
    0.98
     hề
    0.98
    fieurs
    0.97
     azért
    0.97
     optimizations
    0.95
    為に
    0.95
    Activations Density 0.002%

    No Known Activations