© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128227
    Prev
    Next
    INDEX
    Explanations

    The neuron detects standalone numeric list markers—particularly the digit “1” used to label steps, scenes, or headings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    Nebraska Supreme Elizabeth I

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ції
    -1.05
    任何
    -1.02
    تمبر
    -1.00
     HasFactory
    -0.99
    icillin
    -0.99
     from
    -0.98
    negara
    -0.98
    Groeten
    -0.94
    تماد
    -0.94
    maßen
    -0.94
    POSITIVE LOGITS
     his
    1.23
    es
    1.14
    と
    1.13
    ig
    1.10
     первым
    1.07
     negotiations
    1.03
    態度
    1.03
    un
    1.02
     stalwart
    1.02
    为大家
    0.99
    Activations Density 0.000%

    No Known Activations