© 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. 34-GEMMASCOPE-RES-131K
    7. 102601
    Prev
    Next
    INDEX
    Explanations

    ID, Q, VEGF, US keywords

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

    The neuron activates on numeric tokens (digits and multi‐digit numbers) embedded 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_34/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
    Name
    -0.71
    SafeAreaView
    -0.69
    蝦
    -0.67
    intar
    -0.67
    nader
    -0.67
    abort
    -0.66
    個人
    -0.66
    ufel
    -0.66
     that
    -0.65
    individual
    -0.65
    POSITIVE LOGITS
    主键
    1.09
    Sj
    0.88
    瓠
    0.86
    licar
    0.85
    setId
    0.81
     Ida
    0.81
     duty
    0.80
     deltag
    0.78
     działalności
    0.78
    Ena
    0.78
    Activations Density 0.005%

    No Known Activations