© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 98391
    Prev
    Next
    INDEX
    Explanations

    index, units, digit

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

    The neuron fires on numeric tokens (literal numbers) wherever they appear in code or structured 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_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
    ༉
    -1.02
    orsing
    -0.97
    𐍃
    -0.96
    hemiah
    -0.94
    还是
    -0.92
    deras
    -0.90
    הם
    -0.89
    uvres
    -0.88
    Алек
    -0.88
    chtige
    -0.88
    POSITIVE LOGITS
     anh
    0.91
     chili
    0.90
     ce
    0.86
     expr
    0.81
     chat
    0.80
     honor
    0.79
     Ur
    0.78
     arri
    0.77
     a
    0.76
    lık
    0.76
    Activations Density 0.004%

    No Known Activations