© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 23775
    Prev
    Next
    INDEX
    Explanations

    things in lists

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

    The neuron detects category or heading words—single-word labels used to enumerate or classify items (e.g. business/personal, phone/mail, movies/books/TV, age/sex).

    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
     and
    -8.75
     и
    -2.58
    และ
    -2.33
     και
    -2.17
     oraz
    -2.06
     và
    -1.92
     এবং
    -1.91
     및
    -1.91
     และ
    -1.87
    和
    -1.87
    POSITIVE LOGITS
     cioc
    1.73
    ,
    1.70
    toxicity
    1.70
    çou
    1.65
    まりました
    1.60
     fréqu
    1.60
     tinte
    1.60
    まります
    1.59
     sabias
    1.57
     manquer
    1.55
    Activations Density 0.089%

    No Known Activations