© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33096
    Prev
    Next
    INDEX
    Explanations

    hazardous wastes, circuit elements

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

    technical terminology in scientific and technical documents.

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

    This neuron detects specialized technical or scientific jargon terms.

    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
    italien
    -1.16
    —¿
    -1.14
    Besitos
    -1.13
    ärsk
    -1.12
    謌
    -1.10
    カシ
    -1.07
    —¡
    -1.06
     начин
    -1.05
    Iya
    -1.05
    Besos
    -1.05
    POSITIVE LOGITS
     was
    1.08
    љено
    1.07
    倨
    1.05
     noteworthy
    1.02
    了
    1.00
    ฃ
    0.98
    ває
    0.94
     něj
    0.94
     に関する
    0.93
    ƌ
    0.93
    Activations Density 0.535%

    No Known Activations