© 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. 293
    Prev
    Next
    INDEX
    Explanations

    license terms

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

    The neuron strongly responds to software‐license and configuration metadata tokens—e.g. uppercase LICENSE identifiers, version numbers, and code/configuration keywords.

    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
    grunns
    -0.83
     文
    -0.80
    vening
    -0.76
    Indicators
    -0.75
    łon
    -0.75
    emporio
    -0.74
     indicators
    -0.71
    grove
    -0.70
    indicators
    -0.69
    Verizon
    -0.69
    POSITIVE LOGITS
     Centra
    0.64
     liqu
    0.63
     SMART
    0.63
     أمريكي
    0.61
    ッチ
    0.60
    創
    0.60
     Linus
    0.60
    週間
    0.60
    ligner
    0.60
    AddHtmlAttribute
    0.59
    Activations Density 0.043%

    No Known Activations