© 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. 70626
    Prev
    Next
    INDEX
    Explanations

    after "it"

    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
    鵟
    -3.05
    퐿
    -2.73
    趼
    -2.69
    kwür
    -2.55
    饹
    -2.52
     ukon
    -2.47
    ⚢
    -2.47
    ໊
    -2.44
    ixar
    -2.42
    indest
    -2.41
    POSITIVE LOGITS
    的
    3.22
    n
    3.05
     It
    2.63
    [
    2.59
    *
    2.56
    }
    2.53
    á
    2.50
    l
    2.47
    ский
    2.47
    when
    2.39
    Activations Density 0.049%

    No Known Activations