© 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. 10-GEMMASCOPE-RES-131K
    7. 102072
    Prev
    Next
    INDEX
    Explanations

    repeated characters

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

    This neuron detects single-character string tokens (i.e. one-letter literals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     steder
    -1.70
     frukt
    -1.59
     another
    -1.59
     besø
    -1.58
     lienzo
    -1.55
     borbo
    -1.55
     borboleta
    -1.52
    長的
    -1.52
     woda
    -1.51
     morgon
    -1.51
    POSITIVE LOGITS
     to
    1.74
    ⬈
    1.60
     if
    1.60
    はもちろん
    1.58
    amentlich
    1.52
     appliqué
    1.47
     Commencez
    1.45
     ihrer
    1.44
    rivial
    1.43
    璇
    1.41
    Activations Density 0.056%

    No Known Activations