© 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. 22-GEMMASCOPE-RES-131K
    7. 13718
    Prev
    Next
    INDEX
    Explanations

    biological and technical terms

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

    technical and scientific terminology related to systems, software, and biological entities.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on specialized technical and domain‐specific terminology (e.g. electronics, biology, software jargon).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     bezahlt
    -1.16
     хорошая
    -1.05
    hdashline
    -1.03
     “.
    -1.03
     чому
    -1.02
     росій
    -1.01
     เหล
    -1.01
     even
    -1.01
    ㎎
    -0.99
     ایالات
    -0.98
    POSITIVE LOGITS
    ～！
    1.07
    _
    1.05
    〜。
    1.02
     ſ
    1.01
     forskellige
    1.00
    MODAL
    0.99
    Carex
    0.99
    〜！
    0.98
    COURS
    0.96
     című
    0.95
    Activations Density 0.072%

    No Known Activations