© 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. 104989
    Prev
    Next
    INDEX
    Explanations

    comma followed by elaborative phrase

    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
     afspraak
    -1.91
    螣
    -1.88
    ďte
    -1.81
    Recently
    -1.79
     工事
    -1.73
    what
    -1.73
     préfère
    -1.69
     IBRARY
    -1.69
     bidra
    -1.69
     größer
    -1.67
    POSITIVE LOGITS
    </strong>
    2.34
     a
    1.98
     \
    1.96
     “
    1.88
     Its
    1.71
     u
    1.69
     additionally
    1.65
     be
    1.56
     Of
    1.55
     siguiente
    1.55
    Activations Density 0.017%

    No Known Activations