© 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. 107773
    Prev
    Next
    INDEX
    Explanations

    computer science and software licensing

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

    The neuron selectively fires on capitalized, standalone key terms (proper nouns or defined terms) in formal or legal/documentation text, like “Science,” “Software,” or “except” in license boilerplate.

    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
     zarówno
    -0.79
     tentu
    -0.78
    είται
    -0.72
     simbol
    -0.69
     své
    -0.69
     suena
    -0.69
    anmar
    -0.68
     Фу
    -0.67
     barnen
    -0.67
     sweat
    -0.67
    POSITIVE LOGITS
    outSlope
    0.88
    Grupo
    0.87
    налу
    0.84
    áček
    0.83
    verna
    0.82
    woman
    0.82
     chug
    0.81
    yandex
    0.81
    dAtA
    0.80
    ANIM
    0.79
    Activations Density 0.000%

    No Known Activations