© 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. 11004
    Prev
    Next
    INDEX
    Explanations

    Run 2

    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
     There
    -1.56
    (!__
    -1.55
     έχουν
    -1.48
    “
    -1.48
     from
    -1.45
    __);
    -1.43
     vähän
    -1.41
    nieuw
    -1.41
    etCode
    -1.37
    യും
    -1.36
    POSITIVE LOGITS
    (
    1.63
    情况下
    1.43
     impresión
    1.35
     schein
    1.34
    in
    1.34
     dési
    1.32
    НОЕ
    1.31
    過的
    1.30
    いえば
    1.30
    Dichloropropene
    1.29
    Activations Density 0.040%

    No Known Activations