© 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. 364
    Prev
    Next
    INDEX
    Explanations

    technical terms and code syntax

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

    This neuron fires on numeric, version, or identifier‐style tokens (e.g. version numbers, counts, GUID segments, directory 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_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
     Bianchi
    -0.67
     getContent
    -0.66
     implementation
    -0.65
    ativ
    -0.65
    ાર
    -0.65
     darbo
    -0.64
     id
    -0.63
    nder
    -0.63
    Implementation
    -0.62
    aleb
    -0.62
    POSITIVE LOGITS
     Puritan
    0.71
    Vim
    0.71
     milagro
    0.68
    спу
    0.67
     gospodar
    0.66
     farlo
    0.66
    વી
    0.65
    鄺
    0.64
    ַח
    0.64
    ORF
    0.64
    Activations Density 0.070%

    No Known Activations