© 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. 13587
    Prev
    Next
    INDEX
    Explanations

    words before specific endings

    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
    _
    -2.50
    [
    -2.34
    酲
    -2.33
    ен
    -2.33
     zijn
    -2.27
     ascertain
    -2.25
     التي
    -2.22
    our
    -2.20
    an
    -2.17
    as
    -2.17
    POSITIVE LOGITS
    锇
    2.41
    '
    2.34
    寕
    2.31
     飯店
    2.30
     houver
    2.19
     становятся
    2.13
     reinigen
    2.09
     понял
    2.05
     verbinden
    1.98
    鑁
    1.96
    Activations Density 0.000%

    No Known Activations