© 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. 66532
    Prev
    Next
    INDEX
    Explanations

    repeat or again

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

    The neuron fires on tokens that are numeric values (i.e. digits or numbers).

    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
     olhar
    -0.79
     chúng
    -0.77
    erder
    -0.76
    strained
    -0.75
     defesa
    -0.75
    FontOfSize
    -0.75
    nelt
    -0.75
    ент
    -0.73
    tighet
    -0.73
    iduous
    -0.71
    POSITIVE LOGITS
     again
    1.72
     wieder
    1.41
    อีก
    1.32
     снова
    1.16
     another
    1.14
     опять
    1.10
     फिर
    1.09
    Again
    1.09
    again
    1.04
    [::-
    1.00
    Activations Density 0.031%

    No Known Activations