© 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. 84423
    Prev
    Next
    INDEX
    Explanations

    code comments and section starters

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

    The neuron fires on isolated numeric labels and version/section numbers (e.g. line counts, headings, or documentation path numbers).

    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
     by
    -1.14
    :……
    -1.10
     one
    -1.08
     from
    -1.05
    內容簡介
    -1.03
     augus
    -0.99
    相変わらず
    -0.99
     vek
    -0.96
     perde
    -0.96
    特定的
    -0.95
    POSITIVE LOGITS
     }^{
    1.03
    EDEFAULT
    1.02
    dzić
    0.99
     vijf
    0.98
     supporto
    0.97
    CHAPTER
    0.97
    νομα
    0.96
     دیگران
    0.96
    ナル
    0.95
     piensan
    0.95
    Activations Density 0.000%

    No Known Activations