© 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. 22-GEMMASCOPE-RES-131K
    7. 79539
    Prev
    Next
    INDEX
    Explanations

    questions and queries

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

    The neuron strongly activates on long runs of the same character (e.g. repeated “C” tokens), i.e. sequences of repeated identical 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
     or
    -2.14
     which
    -1.77
     this
    -1.75
     with
    -1.74
     if
    -1.73
     so
    -1.66
     when
    -1.59
     after
    -1.55
     one
    -1.55
     just
    -1.51
    POSITIVE LOGITS
     gigantic
    1.60
     wacky
    1.56
    好像是
    1.53
     astonishing
    1.51
     Dinas
    1.50
     tumultuous
    1.46
     dando
    1.45
     astounding
    1.45
     wondrous
    1.45
     whimsical
    1.45
    Activations Density 0.009%

    No Known Activations