© 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. 28484
    Prev
    Next
    INDEX
    Explanations

    product codes

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

    This neuron fires on prominent UI or metadata headings and labels (e.g. dates, section titles, menu items).

    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
     this
    -1.15
     etc
    -1.14
     but
    -1.06
    先は
    -1.05
     on
    -1.04
     elet
    -0.99
     both
    -0.98
    했습니다
    -0.97
     use
    -0.94
    と感じ
    -0.94
    POSITIVE LOGITS
    chea
    1.31
     jdbcTemplate
    1.28
    brainly
    1.27
     nagyobb
    1.25
     például
    1.23
     motoru
    1.22
     voordelen
    1.22
     colorés
    1.15
    ?$
    1.15
    millimeters
    1.15
    Activations Density 0.032%

    No Known Activations