© 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. 109164
    Prev
    Next
    INDEX
    Explanations

    comment variations

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

    The neuron fires on ordinary English content words in natural‐language passages (e.g. prose, commentary, news text) and stays off on programming tokens or code snippets.

    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
     plaza
    -0.85
    Matériel
    -0.85
    Spécification
    -0.81
    Beaucoup
    -0.78
    Cliquez
    -0.76
    Toujours
    -0.75
    isler
    -0.73
    Allez
    -0.73
    Découvrez
    -0.72
    Spécifications
    -0.72
    POSITIVE LOGITS
     comment
    7.16
     comments
    6.53
    comment
    6.22
     Comment
    5.81
    Comment
    5.75
     commented
    5.75
     commenting
    5.72
    comments
    5.19
     COMMENT
    5.06
     Comments
    5.00
    Activations Density 0.214%

    No Known Activations