© 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. 109173
    Prev
    Next
    INDEX
    Explanations

    scientific opinion EF

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

    scientific and technical content related to food safety, regulatory, or research documentation.

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

    The neuron spotlights long sequences of uppercase letters (i.e. acronyms or organizational codes).

    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
     honor
    -0.73
    我只
    -0.70
     honored
    -0.70
     सिद्ध
    -0.69
     Giải
    -0.68
     fiscales
    -0.67
     anlat
    -0.67
     ICI
    -0.66
    Complaints
    -0.66
    قم
    -0.66
    POSITIVE LOGITS
    EF
    1.30
     EF
    1.29
     scientific
    1.19
    Scientific
    1.13
     Opinion
    1.11
     Scientific
    1.09
     opinion
    1.07
    Opinion
    1.05
    scientific
    0.98
    opinion
    0.90
    Activations Density 0.036%

    No Known Activations