© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65672
    Prev
    Next
    INDEX
    Explanations

    hypotheses and arguments

    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
    нью
    -1.55
     sorg
    -1.48
     DÉ
    -1.42
     donner
    -1.41
    ❮
    -1.40
    Ṁ
    -1.37
     elles
    -1.37
     ^{-
    -1.35
    identes
    -1.35
     können
    -1.34
    POSITIVE LOGITS
     about
    2.56
     menschliche
    1.89
     why
    1.86
     that
    1.85
    mathrm
    1.77
    ↵
    1.72
     tentativo
    1.64
     dlaczego
    1.63
     kullanılır
    1.57
     muualla
    1.55
    Activations Density 0.242%

    No Known Activations