© 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. 10-GEMMASCOPE-RES-131K
    7. 14577
    Prev
    Next
    INDEX
    Explanations

    describing effect or composition

    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
     other
    -1.80
     see
    -1.42
    WebElementEntity
    -1.41
     which
    -1.39
    他
    -1.38
     more
    -1.32
     hingga
    -1.32
    drawSprites
    -1.30
     zwierząt
    -1.27
     samband
    -1.27
    POSITIVE LOGITS
     inoltre
    1.51
     أيضا
    1.49
     också
    1.41
     όμως
    1.39
     股份
    1.26
    这几
    1.26
     slav
    1.23
    さてさて
    1.21
     klanten
    1.20
    也很
    1.20
    Activations Density 0.318%

    No Known Activations