© 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. 39518
    Prev
    Next
    INDEX
    Explanations

    new followed by descriptive adjective

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

    The neuron fires on commas immediately preceding numeric measurements (i.e. when a comma is followed by a number).

    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
    橚
    -1.77
     of
    -1.56
    pantalones
    -1.54
     sebuah
    -1.51
     tenté
    -1.50
    珝
    -1.48
     gustado
    -1.42
     the
    -1.41
    鄠
    -1.41
     insuffisamment
    -1.38
    POSITIVE LOGITS
     indirectly
    1.63
     similar
    1.55
     further
    1.55
    oração
    1.48
     include
    1.48
     better
    1.46
     encompassing
    1.45
    zień
    1.45
     technically
    1.45
     adaptar
    1.45
    Activations Density 0.043%

    No Known Activations