© 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. 22341
    Prev
    Next
    INDEX
    Explanations

    programming language syntax

    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
    Beispiele
    -1.72
    équipement
    -1.59
     estadounid
    -1.57
    approche
    -1.56
    淶
    -1.55
    échange
    -1.55
    équilibre
    -1.51
    Dauer
    -1.49
     (_.
    -1.46
    槤
    -1.42
    POSITIVE LOGITS
    閦
    1.58
    ﾛ
    1.39
     This
    1.34
    ࿙
    1.34
    Rptr
    1.34
     berkenaan
    1.32
     who
    1.30
     by
    1.30
     he
    1.30
     dieser
    1.27
    Activations Density 0.013%

    No Known Activations