© 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. 22-GEMMASCOPE-RES-131K
    7. 39157
    Prev
    Next
    INDEX
    Explanations

    null, none, undefined, void, 0

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

    The neuron is triggered by numeric literal tokens (integer or floating‐point numbers) in code, tables, or structured data.

    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
    igay
    -1.02
     carattere
    -0.96
    didSet
    -0.90
     TOK
    -0.86
    lego
    -0.84
    НЫ
    -0.84
    がとても
    -0.84
    ╎
    -0.81
    lieving
    -0.81
     COMPLE
    -0.80
    POSITIVE LOGITS
     zerstört
    0.93
     any
    0.91
     substantial
    0.89
     trendy
    0.89
     stylish
    0.87
     gesagt
    0.87
     żad
    0.87
     sophisticated
    0.85
     frantic
    0.85
     unrelenting
    0.85
    Activations Density 0.009%

    No Known Activations