© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71901
    Prev
    Next
    INDEX
    Explanations

    geometric point

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

    The neuron activates on numeric tokens (integers or decimals), i.e. it detects numbers 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
    nisses
    -1.72
    AFTER
    -1.66
     appels
    -1.63
     réaliser
    -1.62
    ddling
    -1.61
    ]+
    -1.56
     pantalones
    -1.54
    不
    -1.53
     totalement
    -1.53
     azienda
    -1.51
    POSITIVE LOGITS
     cotidiano
    1.74
     whose
    1.73
     pertaining
    1.68
     навіть
    1.66
     with
    1.66
     substantially
    1.63
    棪
    1.63
     because
    1.58
     bolster
    1.53
     garnered
    1.53
    Activations Density 0.031%

    No Known Activations