© 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. 38205
    Prev
    Next
    INDEX
    Explanations

    code structures with closing parenthesis

    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
     可能
    -0.96
     получил
    -0.93
     могут
    -0.93
     erheb
    -0.91
     verurs
    -0.91
     dogged
    -0.91
    際に
    -0.89
     inflexible
    -0.88
     betreff
    -0.86
     here
    -0.86
    POSITIVE LOGITS
    etí
    1.18
    ctica
    1.14
    bord
    1.12
    lazione
    1.04
     sinn
    1.04
    iciar
    1.04
     then
    1.04
     leído
    1.03
    而且
    1.01
     ARISING
    1.00
    Activations Density 0.007%

    No Known Activations