© 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. 33692
    Prev
    Next
    INDEX
    Explanations

    quality and results

    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
     السياس
    -0.96
     imposible
    -0.96
    ennas
    -0.94
    JsonFormat
    -0.94
    Slf
    -0.94
    RTSN
    -0.88
    omorphisms
    -0.88
     département
    -0.87
    dataIndex
    -0.87
    เพื่อ
    -0.87
    POSITIVE LOGITS
     results
    1.21
     quality
    1.18
     will
    1.18
     afterwards
    1.16
     result
    1.13
     risultato
    1.13
     outcome
    1.13
     resulting
    1.12
     đẹp
    1.09
     finished
    1.09
    Activations Density 0.125%

    No Known Activations