© 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. 74535
    Prev
    Next
    INDEX
    Explanations

    initiation of clauses or listing

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

    The neuron flags standalone numeric tokens (e.g. digits and numbering labels) 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
     by
    -2.17
     to
    -2.06
     even
    -1.83
     there
    -1.76
     in
    -1.71
    </h2>
    -1.71
     make
    -1.60
     before
    -1.53
     then
    -1.52
     new
    -1.49
    POSITIVE LOGITS
    摃
    1.59
     fokus
    1.47
    Fotografía
    1.46
     bendera
    1.41
    лятор
    1.38
    它的
    1.38
     maniac
    1.37
     Dokter
    1.35
    ⡰
    1.34
    麃
    1.34
    Activations Density 0.480%

    No Known Activations