© 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. 79729
    Prev
    Next
    INDEX
    Explanations

    base/ followed by path

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

    The neuron fires on occurrences of the identifier “base” in C/C++ include‐path tokens.

    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
     on
    -1.80
     from
    -1.68
     all
    -1.61
     or
    -1.59
     this
    -1.52
     so
    -1.49
     in
    -1.48
    子さん
    -1.46
     its
    -1.40
     went
    -1.39
    POSITIVE LOGITS
     Dinas
    1.56
    however
    1.44
    op
    1.38
    k
    1.38
     alcune
    1.34
     ayur
    1.34
    Allgemeine
    1.34
     REALLY
    1.32
    Татьяна
    1.32
     diversos
    1.31
    Activations Density 0.000%

    No Known Activations