© 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. 35677
    Prev
    Next
    INDEX
    Explanations

    document titles and headings

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

    The neuron specifically fires on longer multi‐digit numeric sequences (e.g., timestamps, ID codes, or other number strings).

    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
     it
    -1.29
     since
    -1.20
     There
    -1.17
     should
    -1.17
     large
    -1.14
    There
    -1.14
     Every
    -1.12
     from
    -1.11
     When
    -1.11
    If
    -1.09
    POSITIVE LOGITS
     abd
    1.14
     nyingi
    1.13
     женщины
    1.11
     yetu
    1.08
    えっ
    1.05
     Fasting
    1.00
    espół
    1.00
    ¹,
    0.99
     trám
    0.99
    mml
    0.99
    Activations Density 0.000%

    No Known Activations