© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 84366
    Prev
    Next
    INDEX
    Explanations

    compiler error codes

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

    The neuron detects numeric tokens (number literals) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     from
    -1.21
     will
    -1.10
     of
    -1.07
     get
    -1.07
     any
    -1.06
     for
    -1.04
     all
    -1.01
     got
    -1.00
     became
    -0.99
    明白了
    -0.98
    POSITIVE LOGITS
     alltid
    1.33
     utiliser
    1.28
    푆
    1.24
     búsquedas
    1.23
     éviter
    1.21
     dénon
    1.19
     réjou
    1.18
     rapporter
    1.17
    استفاده
    1.15
    もありますが
    1.13
    Activations Density 0.005%

    No Known Activations