© 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. 71552
    Prev
    Next
    INDEX
    Explanations

    names followed by other names or words

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

    The neuron fires on tokens composed entirely of uppercase letters or symbols (e.g. acronyms like “HC” or math delimiters like “$”).

    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
    The
    -2.44
    が
    -2.22
    an
    -2.20
    It
    -2.20
    In
    -2.14
    the
    -2.06
    What
    -2.06
    is
    -2.06
    ed
    -2.02
    Despite
    -2.02
    POSITIVE LOGITS
     and
    3.17
     protože
    2.08
    messung
    2.02
    轱
    1.96
    🫅
    1.95
    França
    1.93
     เรา
    1.91
     pretože
    1.89
     květ
    1.85
    菝
    1.81
    Activations Density 0.000%

    No Known Activations