© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67158
    Prev
    Next
    INDEX
    Explanations

    apricot, apricot, apricot, apricot, apricot, apricot

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

    The neuron fires most strongly on technical material or chemical compound names (e.g. zein, oleic acid) indicating it detects mentions of specific substances.

    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
     kompeti
    -1.20
     lte
    -1.13
     mengen
    -1.13
     vocale
    -1.11
     autonome
    -1.10
    :{
    -1.10
    УДК
    -1.09
    ꉂ
    -1.08
     berbagai
    -1.08
    /…
    -1.06
    POSITIVE LOGITS
     both
    1.30
     each
    1.29
     EconPapers
    1.21
    なもの
    1.19
     group
    1.17
     category
    1.16
     overall
    1.15
     our
    1.15
     series
    1.14
     manicura
    1.12
    Activations Density 0.054%

    No Known Activations