© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74833
    Prev
    Next
    INDEX
    Explanations

    the followed by a noun

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

    This neuron activates on numeric tokens, spotting sequences of digits (including multi‐digit numbers and decimals).

    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
     stemming
    -1.76
     अलावा
    -1.71
     cuchara
    -1.70
    魉
    -1.66
     vē
    -1.66
     если
    -1.65
    </h4>
    -1.65
    ociação
    -1.60
     laikā
    -1.59
     and
    -1.58
    POSITIVE LOGITS
     you
    2.47
    {
    2.13
    id
    1.71
    three
    1.69
     Technically
    1.65
    $
    1.65
    9
    1.63
    C
    1.62
    2
    1.61
    很高
    1.59
    Activations Density 0.122%

    No Known Activations