© 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. 11788
    Prev
    Next
    INDEX
    Explanations

    common verb phrases

    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
     to
    -1.70
     will
    -1.64
    Some
    -1.45
    ！）
    -1.38
     can
    -1.28
     are
    -1.28
    };
    -1.27
     which
    -1.25
     kürzlich
    -1.24
     />
    -1.23
    POSITIVE LOGITS
    kkor
    1.38
     mesma
    1.29
     vasto
    1.23
     hogares
    1.23
     devrait
    1.23
    eschön
    1.22
    了下去
    1.21
     ejer
    1.20
    skrä
    1.20
    ひた
    1.19
    Activations Density 0.372%

    No Known Activations