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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42154
    Prev
    Next
    INDEX
    Explanations

    to the Noun

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

    The neuron fires on numeric measurement tokens (e.g. distances, lengths, coordinates).

    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
     was
    -2.59
    了一个
    -2.45
    cayaan
    -2.41
     $
    -2.38
     includes
    -2.19
     other
    -2.08
     wodurch
    -1.97
     womit
    -1.91
    便捷
    -1.89
     tensão
    -1.86
    POSITIVE LOGITS
    medriver
    2.38
     چگونه
    2.31
    дельник
    2.28
    蜮
    2.28
    ㉓
    2.27
     навіть
    2.25
     décider
    2.25
    ጐ
    2.19
    蕻
    2.19
     nawet
    2.19
    Activations Density 0.134%

    No Known Activations