© 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. 111832
    Prev
    Next
    INDEX
    Explanations

    legal and technical contexts

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

    The neuron activates on comma punctuation marks.

    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
     corrom
    -1.80
     acheter
    -1.73
     achat
    -1.68
    !»
    -1.66
     incrí
    -1.65
     enrique
    -1.64
     marta
    -1.63
     Inſ
    -1.62
     ſont
    -1.60
     lavable
    -1.59
    POSITIVE LOGITS
     without
    2.22
     and
    1.83
     with
    1.80
     while
    1.76
     before
    1.70
     Еще
    1.65
     ње
    1.62
     включая
    1.48
     Another
    1.41
     njego
    1.41
    Activations Density 0.000%

    No Known Activations