© 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. 39681
    Prev
    Next
    INDEX
    Explanations

    Eureka!!Cast metalAdele makesTrek inNeurokinin

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

    The neuron detects code identifiers that include an underscore followed by numeric suffixes (e.g. variable names like “p_i188”).

    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
     only
    -1.35
     (
    -1.34
     which
    -1.27
     that
    -1.22
     when
    -1.14
     where
    -1.12
    autoIncrement
    -1.09
     môže
    -1.09
     who
    -1.09
    ！！」
    -1.09
    POSITIVE LOGITS
    還要
    1.18
    還沒
    1.15
     entw
    1.14
    也會
    1.12
    ほとん
    1.10
    还要
    1.10
     ardent
    1.10
     tarn
    1.10
     unn
    1.09
    还得
    1.09
    Activations Density 0.000%

    No Known Activations