© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68964
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

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

    This neuron activates on numeric literals (digits and multi‐digit numbers) 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_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
     такого
    -0.88
    malı
    -0.86
    toHave
    -0.85
    ādā
    -0.84
    Asm
    -0.82
    ఝ
    -0.80
     discerned
    -0.80
     PEL
    -0.79
    胥
    -0.77
     Kemp
    -0.77
    POSITIVE LOGITS
     their
    1.20
    ála
    1.02
    plays
    1.00
    jsxFileName
    0.98
    اير
    0.96
     их
    0.96
     cỏ
    0.94
    When
    0.91
    biased
    0.91
    when
    0.90
    Activations Density 0.001%

    No Known Activations