© 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. 25754
    Prev
    Next
    INDEX
    Explanations

    California Rules of Court

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

    The neuron fires on content-bearing, domain-specific terms (e.g. technical nouns, proper names, and formal vocabulary) rather than on common function words.

    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
    legt
    -0.69
    ServiceName
    -0.69
    ⟵
    -0.66
     utafiti
    -0.64
     Nicho
    -0.63
    bigg
    -0.63
     Deadpool
    -0.63
     Boating
    -0.63
    läng
    -0.63
    kháu
    -0.63
    POSITIVE LOGITS
     пусты
    0.70
    arkov
    0.69
    ам
    0.68
     thơm
    0.66
    安静
    0.66
     Hud
    0.66
    rgba
    0.65
    痛い
    0.65
    IconButton
    0.63
    nemen
    0.63
    Activations Density 0.056%

    No Known Activations