© 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. 11832
    Prev
    Next
    INDEX
    Explanations

    articles and stories

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

    This neuron fires on numeric tokens (digits and digit sequences) in URL-like paths, such as article or resource IDs.

    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
     setPassword
    -0.87
    lags
    -0.84
    ällningar
    -0.82
    tionally
    -0.82
    onsumsi
    -0.77
    工作室
    -0.77
     tyme
    -0.76
    existsSync
    -0.76
     RANGE
    -0.75
    crats
    -0.75
    POSITIVE LOGITS
    Pilih
    0.87
    請繼續
    0.85
     Offshore
    0.79
    𝒜
    0.79
    σκε
    0.79
    Minus
    0.79
    aunque
    0.79
    驕
    0.79
    还不错
    0.79
    なのです
    0.79
    Activations Density 0.021%

    No Known Activations