© 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. 22-GEMMASCOPE-RES-131K
    4. 66569
    Prev
    Next
    INDEX
    Explanations

    code, questions, and statements

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

    The neuron is firing on tokens that look like schema or code identifiers (e.g. JSON/document field names and variable/property names).

    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
     when
    -1.35
     all
    -1.28
    Crítica
    -1.27
    
    -1.27
     it
    -1.26
     or
    -1.23
     ALL
    -1.16
     without
    -1.13
     вниз
    -1.06
     lel
    -1.05
    POSITIVE LOGITS
     carreaux
    1.24
    ちょこ
    1.18
     alho
    1.17
     réessayer
    1.16
     welchen
    1.14
    TypedDataSet
    1.13
    налу
    1.12
     maniere
    1.10
     welchem
    1.09
    ishes
    1.05
    Activations Density 0.000%

    No Known Activations