© 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. 111654
    Prev
    Next
    INDEX
    Explanations

    [noun] of [noun]

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

    The neuron detects numeric tokens (standalone numbers or 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
    -1.95
     jahr
    -1.91
    粜
    -1.89
     fiables
    -1.84
    sandalias
    -1.74
    悫
    -1.73
    ⡪
    -1.66
     sourire
    -1.63
     quinze
    -1.60
     inond
    -1.59
    POSITIVE LOGITS
     also
    2.66
     may
    1.84
     також
    1.83
     not
    1.82
    </em>
    1.82
     sometimes
    1.77
     more
    1.74
     relatively
    1.74
    </h4>
    1.68
     usually
    1.68
    Activations Density 0.181%

    No Known Activations