© 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. 90381
    Prev
    Next
    INDEX
    Explanations

    format specifiers like `%d` or `%lf`

    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
     who
    -1.91
     hemd
    -1.82
     tilgjenge
    -1.70
     marki
    -1.70
     ucha
    -1.69
     fulfilling
    -1.66
     problemen
    -1.66
     that
    -1.66
    mpagne
    -1.65
     tega
    -1.61
    POSITIVE LOGITS
    </strong>
    2.45
    These
    2.33
    Because
    1.96
    7
    1.95
    Being
    1.89
    Those
    1.88
    6
    1.84
    DESCRIPCIÓN
    1.79
    9
    1.77
    This
    1.73
    Activations Density 0.006%

    No Known Activations