© 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. 34-GEMMASCOPE-RES-131K
    4. 80816
    Prev
    Next
    INDEX
    Explanations

    writing program Creative Writing MFA Programs

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

    The neuron is strongly activated by standalone numeric tokens (digits or 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_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
    bióticos
    -1.07
    %!
    -1.03
    
    -0.96
     by
    -0.90
    -^
    -0.90
    ...?"
    -0.89
    谣
    -0.85
    ...!
    -0.85
    backButton
    -0.85
    nictví
    -0.83
    POSITIVE LOGITS
    The
    1.21
    We
    1.09
     ($('#
    1.01
    ै
    1.00
     CERTAIN
    0.99
    дьми
    0.95
    download
    0.94
    If
    0.93
    woners
    0.92
    Več
    0.92
    Activations Density 0.002%

    No Known Activations