© 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. 104588
    Prev
    Next
    INDEX
    Explanations

    multi-lingual technical descriptions

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

    The neuron detects occurrences of the “re-” prefix (as in “re-release”), marking words that begin with re-.

    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
    ParallelGroup
    -1.08
    すでに
    -0.95
     zahlreiche
    -0.94
     zahlreichen
    -0.94
    роятно
    -0.94
     all
    -0.94
     __
    -0.93
    Jereo
    -0.93
    ária
    -0.93
     आवश्यकता
    -0.92
    POSITIVE LOGITS
    küche
    1.26
    bekah
    1.02
     prendere
    1.02
     meravigli
    0.98
     proposto
    0.94
    んじゃ
    0.93
     krzy
    0.93
     piú
    0.93
     faceva
    0.92
    zusch
    0.91
    Activations Density 0.000%

    No Known Activations