© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7449
    Prev
    Next
    INDEX
    Explanations

    section headers or Q/A starters

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

    The neuron detects floating‐point numeric literals (numbers containing a decimal point).

    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
     Türkçe
    -1.70
     necessária
    -1.66
     koska
    -1.62
     kanske
    -1.62
     poupée
    -1.60
     Eliminar
    -1.59
    PRIMER
    -1.58
     HISTORIA
    -1.57
    porque
    -1.56
     dentelle
    -1.56
    POSITIVE LOGITS
     and
    2.03
     between
    2.02
    ichtete
    1.55
    ,"%
    1.51
    bosky
    1.50
     one
    1.49
     neither
    1.45
    jogador
    1.44
    ка
    1.44
    ?,?,
    1.39
    Activations Density 0.001%

    No Known Activations