© 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. 34-GEMMASCOPE-RES-131K
    7. 65943
    Prev
    Next
    INDEX
    Explanations

    asset filenames, technical terms, foreign words

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

    The neuron fires on numeric tokens (digits or numbers) embedded in resource‐style identifiers—e.g. version numbers, scale qualifiers, or numeric suffixes in file‐name strings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    swig
    -0.79
    ardo
    -0.78
     Fakult
    -0.76
    стен
    -0.75
     modelAndView
    -0.72
    nicas
    -0.72
    ЧЕСКИ
    -0.72
     models
    -0.71
     morph
    -0.70
    앉
    -0.70
    POSITIVE LOGITS
     proposées
    0.90
    ącz
    0.89
    stare
    0.81
     compétences
    0.80
    chemia
    0.79
    pressing
    0.78
    默认
    0.77
     @"
    0.77
    btn
    0.76
    iterranean
    0.76
    Activations Density 0.009%

    No Known Activations