© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19011
    Prev
    Next
    INDEX
    Explanations

    you know my name

    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
     pantalón
    -1.63
     use
    -1.62
    鰐
    -1.53
    Its
    -1.52
    ).
    -1.52
    想了想
    -1.51
     décider
    -1.48
     though
    -1.44
     emporter
    -1.43
    tafogo
    -1.41
    POSITIVE LOGITS
    !”
    1.55
    !!!
    1.53
    Genial
    1.50
     again
    1.47
    。”
    1.42
    :['
    1.33
    Groet
    1.33
     komunikasi
    1.33
     storie
    1.31
    ጺ
    1.30
    Activations Density 0.043%

    No Known Activations