© 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. 103361
    Prev
    Next
    INDEX
    Explanations

    free software licenses

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

    The neuron responds to numeric tokens—particularly multi‐digit numbers (e.g. years, IDs, phone numbers) in code or 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
     Cote
    -0.66
     VERSION
    -0.66
    只需
    -0.65
    Yung
    -0.65
     broadly
    -0.65
     CRUZ
    -0.64
    smh
    -0.64
     Gabel
    -0.64
     mvc
    -0.63
    ása
    -0.63
    POSITIVE LOGITS
    Banks
    0.79
     Scho
    0.76
     Banks
    0.76
    함
    0.72
     banks
    0.71
    amy
    0.69
    trust
    0.69
    ()];
    0.68
    четов
    0.68
     réaliste
    0.68
    Activations Density 0.051%

    No Known Activations