© 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. 10712
    Prev
    Next
    INDEX
    Explanations

    @(Html.Kendo()...)'

    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
    𓂅
    -2.06
     “
    -2.06
     usually
    -2.03
    馀
    -2.03
     referred
    -2.00
    入って
    -1.98
     found
    -1.95
     now
    -1.94
     from
    -1.93
     In
    -1.93
    POSITIVE LOGITS
    actéristi
    3.06
    锨
    2.78
    卧槽
    2.64
    僰
    2.64
    IGHTS
    2.61
    岨
    2.52
    儇
    2.48
    擽
    2.47
     enfati
    2.42
    ſu
    2.42
    Activations Density 0.001%

    No Known Activations