© 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. 66964
    Prev
    Next
    INDEX
    Explanations

    variables and code constructs

    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
    Cevap
    -1.54
     them
    -1.47
     erstes
    -1.45
    amerikanische
    -1.32
    pezifische
    -1.30
     mereka
    -1.30
    🎦
    -1.30
    他们
    -1.30
     their
    -1.30
    zeugen
    -1.28
    POSITIVE LOGITS
    Ꮀ
    1.59
     gostaria
    1.41
    riwal
    1.36
     todavía
    1.35
     quedarse
    1.33
     verfügt
    1.33
     $-$
    1.30
     conhece
    1.29
    ionado
    1.28
    >
    1.28
    Activations Density 0.001%

    No Known Activations