© 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. 10-GEMMASCOPE-RES-131K
    4. 39259
    Prev
    Next
    INDEX
    Explanations

    of [word]

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

    The neuron detects mentions of procedural or methodological terms (e.g. process, method, procedure).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    èces
    -1.42
    ueves
    -1.31
    请问
    -1.20
     zpě
    -1.19
     второго
    -1.16
     üç
    -1.16
    卧槽
    -1.16
    annels
    -1.14
    assemblée
    -1.13
    inoza
    -1.12
    POSITIVE LOGITS
     certain
    1.42
     potra
    1.34
     another
    1.34
    
    1.30
    if
    1.30
    Ű
    1.25
     genoux
    1.23
    がみ
    1.20
    رژی
    1.16
     extraordinaire
    1.13
    Activations Density 0.181%

    No Known Activations