© 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. 22-GEMMASCOPE-RES-131K
    7. 12682
    Prev
    Next
    INDEX
    Explanations

    opinions and observations

    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_22/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
     এবং
    -0.94
     exceptionally
    -0.91
    baca
    -0.90
     Gnade
    -0.88
     possono
    -0.88
    gnar
    -0.88
     univariate
    -0.85
    ਘ
    -0.85
    ebilir
    -0.85
     equit
    -0.85
    POSITIVE LOGITS
     always
    1.58
     sometimes
    1.27
     ALWAYS
    1.22
     will
    1.19
     завжди
    1.10
     Sometimes
    1.09
     often
    1.05
     still
    1.05
     just
    1.02
    Always
    1.01
    Activations Density 0.027%

    No Known Activations