© 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. 129912
    Prev
    Next
    INDEX
    Explanations

    error codes

    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
     завжди
    -1.07
    sej
    -1.04
    bagno
    -1.04
    roaches
    -1.02
    cC
    -1.01
     Erlebn
    -1.00
    vám
    -0.99
     découvre
    -0.98
     sempre
    -0.98
    justice
    -0.97
    POSITIVE LOGITS
     ['
    1.04
    b
    0.97
    1
    0.96
    Ĩ
    0.94
    uyer
    0.94
     двер
    0.94
    u
    0.94
    :'/
    0.93
    okka
    0.93
    ["
    0.92
    Activations Density 0.011%

    No Known Activations