© 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. 11232
    Prev
    Next
    INDEX
    Explanations

    default values or settings

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

    The neuron activates on numeric literals (integers or decimals), i.e. sequences of digits (and optional decimal points).

    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
     \{
    -1.78
    </strong>
    -1.67
    </em>
    -1.55
     defunct
    -1.54
     genauer
    -1.51
    ˗
    -1.48
    CodeDom
    -1.45
    uzu
    -1.43
     novices
    -1.43
                
    -1.43
    POSITIVE LOGITS
     doesn
    1.84
     isn
    1.69
     default
    1.65
    Default
    1.56
    default
    1.55
     usare
    1.55
     seems
    1.52
     won
    1.52
     also
    1.51
     miſ
    1.49
    Activations Density 0.045%

    No Known Activations