© 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. 119489
    Prev
    Next
    INDEX
    Explanations

    my name is

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     who
    -1.97
    鯪
    -1.84
     which
    -1.84
    atever
    -1.73
     with
    -1.73
     whose
    -1.72
     CALIFORNI
    -1.70
     który
    -1.65
    autogui
    -1.65
     garagem
    -1.63
    POSITIVE LOGITS
     
    2.11
     assurer
    1.59
    なぜか
    1.58
    了过去
    1.52
    Estas
    1.45
    又は
    1.39
     obtend
    1.39
     [
    1.39
    久しぶり
    1.38
    艰难
    1.38
    Activations Density 0.030%

    No Known Activations