© 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. 3722
    Prev
    Next
    INDEX
    Explanations

    if you

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

    the neuron detects numeric tokens (numbers, including integers and decimals) in the text.

    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
     of
    -2.05
     by
    -1.57
    Your
    -1.49
    　　《
    -1.44
     meiner
    -1.42
    ゛
    -1.40
    ,
    -1.39
     يعرف
    -1.38
     membuat
    -1.35
    flowered
    -1.35
    POSITIVE LOGITS
    >
    1.80
    </
    1.80
     his
    1.77
    }
    1.76
    <
    1.61
    )
    1.52
     its
    1.52
    ”.
    1.48
    ;
    1.48
     these
    1.45
    Activations Density 0.076%

    No Known Activations