© 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. 22-GEMMASCOPE-RES-131K
    7. 35919
    Prev
    Next
    INDEX
    Explanations

    Commercial software license

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

    The neuron fires strongly on standalone, capitalized keywords and section‐heading terms (e.g. “Contact,” “License,” “Version,” “Convert,” etc.) typically used in code comment headers and legal/license blocks.

    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
     all
    -1.82
     other
    -1.79
     on
    -1.73
     even
    -1.68
     their
    -1.62
     only
    -1.62
     first
    -1.53
     from
    -1.53
    ↵↵
    -1.52
     despite
    -1.51
    POSITIVE LOGITS
    ではでは
    1.63
    ⚋
    1.56
    ごま
    1.44
     colorés
    1.42
    unków
    1.40
    ではまた
    1.39
    躄
    1.38
     veranderen
    1.38
    cerne
    1.37
     reconoció
    1.35
    Activations Density 0.113%

    No Known Activations