© 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. 42622
    Prev
    Next
    INDEX
    Explanations

    numbers following units

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

    The neuron fires on the digit “0’’ when it appears as the leading part of a decimal fraction (i.e. numbers less than 1 written with a “0.”).

    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
     But
    -2.67
     It
    -2.63
     to
    -2.59
     been
    -2.30
     The
    -2.22
     So
    -2.22
     according
    -2.19
     Its
    -2.13
     because
    -2.13
     in
    -2.13
    POSITIVE LOGITS
    焢
    2.44
     menek
    2.41
     bicicleta
    2.38
    ikuti
    2.27
     şir
    2.22
     Rabu
    2.16
     rése
    2.16
     meres
    2.14
     conster
    2.14
     Wilayah
    2.13
    Activations Density 0.028%

    No Known Activations