© 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. 23781
    Prev
    Next
    INDEX
    Explanations

    dependent: :destroy

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

    The neuron fires on standalone numerals (digits or number tokens) such as years, version numbers, section or figure numbers, etc.

    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
     αγ
    -0.75
    setName
    -0.73
    bili
    -0.73
    nam
    -0.70
    כות
    -0.69
    canActivate
    -0.68
     closing
    -0.67
    woff
    -0.66
    ouch
    -0.65
    itoneum
    -0.65
    POSITIVE LOGITS
    êle
    0.70
     Eriksson
    0.69
     Hohe
    0.69
    ತ್
    0.67
     大学
    0.66
     pedagang
    0.65
    اسی
    0.64
    tabak
    0.63
     għ
    0.63
    muda
    0.63
    Activations Density 0.073%

    No Known Activations