© 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. 363
    Prev
    Next
    INDEX
    Explanations

    numbers, amounts, and ranges

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

    The neuron fires on numeric and quantitative expressions—numbers, comparative words (like “from,” “greater,” “above,” “by a”), and their associated measurement units.

    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
     AppColors
    -0.99
     vedea
    -0.94
     you
    -0.85
    racin
    -0.85
    Dimethyl
    -0.80
     occaf
    -0.76
    XFF
    -0.74
    йна
    -0.73
     wasn
    -0.73
     cowok
    -0.73
    POSITIVE LOGITS
    Ꮞ
    0.97
     solcher
    0.88
     whopping
    0.87
    itzt
    0.86
     любого
    0.86
    ZERO
    0.85
     ≤
    0.84
    assertEquals
    0.84
     equal
    0.84
     ranging
    0.83
    Activations Density 0.099%

    No Known Activations