© 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. 59423
    Prev
    Next
    INDEX
    Explanations

    lug

    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
     estekak
    -2.92
     you
    -2.73
    }{
    -2.53
     bidra
    -2.45
     möjlighet
    -2.42
     öppna
    -2.34
    vantaged
    -2.33
     現貨
    -2.33
     lära
    -2.22
    鋮
    -2.22
    POSITIVE LOGITS
     be
    2.95
     …
    2.75
    能在
    2.38
    𐬹
    2.31
     stalwart
    2.30
    匍
    2.28
     soaring
    2.14
     respective
    2.13
    翃
    2.06
     gravely
    2.05
    Activations Density 0.001%

    No Known Activations