© 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. 22-GEMMASCOPE-RES-131K
    7. 73324
    Prev
    Next
    INDEX
    Explanations

    HTML, JSON, code, and text snippets

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

    The main thing this neuron does is find numerical literals (tokens representing numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     biela
    -1.08
     its
    -1.07
     módulos
    -1.02
     japones
    -0.98
     armado
    -0.97
     esponja
    -0.97
     Escolar
    -0.96
     delito
    -0.96
     escote
    -0.96
     FRANCIS
    -0.95
    POSITIVE LOGITS
     aforementioned
    1.05
    是怎么回事
    0.99
    ics
    0.98
     एक
    0.98
    rio
    0.98
     Man
    0.96
    工作人员
    0.94
     этими
    0.93
     [],
    0.93
     amd
    0.92
    Activations Density 0.016%

    No Known Activations