© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59474
    Prev
    Next
    INDEX
    Explanations

    abbreviations followed by periods

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

    This neuron fires on tokens that consist of a single uppercase letter followed by a period and a sequence of digits (e.g. “V.548,” “C.2416,” “S.2336”).

    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
    preuves
    -1.05
    kinh
    -1.03
     ***!
    -1.02
    ◜
    -1.02
    thiet
    -1.02
     nepiecieš
    -0.98
    اتي
    -0.98
    点此
    -0.96
    Ufficio
    -0.95
    ències
    -0.94
    POSITIVE LOGITS
    .,
    1.77
    .;
    1.52
    .);
    1.28
    .-
    1.27
    ./
    1.25
    .:
    1.25
    .,"
    1.23
    .),
    1.21
    .
    1.10
    .');
    1.05
    Activations Density 0.096%

    No Known Activations