© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 20467
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming symbols

    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
     =-\
    -1.77
     любых
    -1.70
    ING
    -1.69
    \
    -1.59
    </strong>
    -1.56
     ''}
    -1.54
    ごはん
    -1.52
    龶
    -1.52
     mesures
    -1.52
     '-')
    -1.51
    POSITIVE LOGITS
     a
    1.96
     they
    1.68
    ↵
    1.64
     that
    1.55
     these
    1.51
     or
    1.50
     doesn
    1.49
    %);
    1.44
     aguj
    1.41
     your
    1.39
    Activations Density 0.143%

    No Known Activations