© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69954
    Prev
    Next
    INDEX
    Explanations

    Success | Acc

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

    This neuron fires on numeric tokens (including numbers with decimals) used as data entries in ASCII-style tables.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    Coucou
    -1.64
    bonsoir
    -1.63
    昙
    -1.60
    Ком
    -1.54
     princesa
    -1.50
    脍
    -1.50
    Каждый
    -1.49
    Чу
    -1.49
    Ку
    -1.48
    Коро
    -1.45
    POSITIVE LOGITS
     is
    1.63
     только
    1.55
     The
    1.48
     После
    1.35
    with
    1.34
    gazette
    1.30
    reff
    1.26
    ristiano
    1.24
    MAXN
    1.24
     amid
    1.23
    Activations Density 0.016%

    No Known Activations