© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15905
    Prev
    Next
    INDEX
    Explanations

    reiteration and reminders

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

    This neuron detects words that emphasize repetition or doing something again (e.g., “time,” “again,” “more,” “repeat”).

    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
     some
    -1.09
     different
    -1.03
     possibly
    -0.99
     Immediately
    -0.95
     usually
    -0.94
    ANGES
    -0.94
    argv
    -0.92
     typically
    -0.91
     Apparently
    -0.91
     immediately
    -0.91
    POSITIVE LOGITS
    一遍
    1.27
     reiterated
    1.20
    again
    1.16
     reiterate
    1.08
     повтор
    1.07
     "$@"
    1.02
     why
    1.02
     reminder
    1.02
     again
    1.00
    ghana
    0.98
    Activations Density 0.016%

    No Known Activations