© 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. 59845
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and inequalities

    np_acts-logits-general · gemini-2.5-flash-lite

    the presence of numeric literals (integers or decimals) in mathematical expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     ブラウン
    -1.88
    "+
    -1.77
     alleged
    -1.77
    </em>
    -1.74
    first
    -1.63
     lunghi
    -1.62
     upcoming
    -1.60
     frantic
    -1.59
    what
    -1.58
     our
    -1.55
    POSITIVE LOGITS
    ’
    2.17
     ermöglicht
    1.84
    ,.
    1.81
    /"
    1.80
    -*
    1.68
    '
    1.59
    ,..
    1.56
    潆
    1.54
     MUCH
    1.53
    的心情
    1.53
    Activations Density 0.009%

    No Known Activations