© 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. 87130
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers and code snippets

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

    The neuron fires on unusually long runs of space characters (e.g. indentation or padding whitespace).

    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
    -
    -2.13
    li
    -1.55
    f
    -1.52
     alebo
    -1.50
    Или
    -1.49
    一个小
    -1.47
    d
    -1.47
    倆
    -1.45
    n
    -1.40
    elif
    -1.38
    POSITIVE LOGITS
     such
    1.85
     you
    1.67
    ecé
    1.57
     and
    1.55
     sekarang
    1.54
    łgorzata
    1.49
     everything
    1.48
    zapatilla
    1.45
    raseña
    1.44
    licópter
    1.41
    Activations Density 0.008%

    No Known Activations