© 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. 10-GEMMASCOPE-RES-131K
    7. 43722
    Prev
    Next
    INDEX
    Explanations

    system tracing and performance analysis

    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_10/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
     erforder
    -1.25
    噼
    -1.23
     orchestrated
    -1.19
     inoxydable
    -1.19
    少なくとも
    -1.18
     remnants
    -1.16
    擰
    -1.16
    绺
    -1.12
     imparting
    -1.09
     deft
    -1.08
    POSITIVE LOGITS
    roots
    1.22
     benar
    1.14
     publié
    1.13
    pathic
    1.13
     Berlín
    1.11
    LoggerFactory
    1.11
     diciembre
    1.11
     your
    1.10
    ÇO
    1.09
    雳
    1.09
    Activations Density 0.057%

    No Known Activations