© 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. 39339
    Prev
    Next
    INDEX
    Explanations

    repeat an action

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

    The neuron flags tokens that signal a “re-” repetition or redo—i.e. words beginning with the re- prefix that denote trying again or revisiting something.

    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
     zurückge
    -1.05
    派的
    -1.05
     finally
    -1.05
    之一
    -1.00
    きち
    -0.98
    事前に
    -0.97
     тоже
    -0.93
     заранее
    -0.93
    ようになって
    -0.92
     bâtiments
    -0.92
    POSITIVE LOGITS
     with
    1.45
     in
    1.30
     médica
    0.93
    😮
    0.86
    malige
    0.85
     recomand
    0.85
    фици
    0.85
    marty
    0.84
     without
    0.84
     sans
    0.84
    Activations Density 0.059%

    No Known Activations