© 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. 130949
    Prev
    Next
    INDEX
    Explanations

    as with a following word

    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
    ↵↵
    -1.72
    jenigen
    -1.69
     justo
    -1.68
    いろいろ
    -1.55
    ほか
    -1.55
     
    -1.52
     
    -1.52
    震撼
    -1.49
     связанные
    -1.47
    ᨁ
    -1.47
    POSITIVE LOGITS
     each
    2.36
     their
    2.03
     with
    1.79
     these
    1.73
     our
    1.62
     saranno
    1.61
     =
    1.55
     even
    1.45
    我这
    1.44
     one
    1.43
    Activations Density 0.020%

    No Known Activations