© 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. 12052
    Prev
    Next
    INDEX
    Explanations

    `string` data types and code snippets

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

    The neuron predominantly fires on punctuation/operator tokens—especially colons (":"), equals signs ("="), plus signs ("+"), and similar symbols used to separate or assign values in code.

    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
     Aprile
    -0.75
     ноября
    -0.74
     Crown
    -0.73
    ਿ
    -0.72
     سواری
    -0.71
    xsi
    -0.71
    PyExc
    -0.71
    }_{(
    -0.71
    жела
    -0.70
     investors
    -0.69
    POSITIVE LOGITS
    string
    1.11
     string
    1.05
    字符串
    0.94
    शि
    0.84
     bytes
    0.79
     dwind
    0.77
    bytes
    0.76
     Dougherty
    0.75
     nước
    0.74
     intenta
    0.73
    Activations Density 0.001%

    No Known Activations