© 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. 3846
    Prev
    Next
    INDEX
    Explanations

    place names and surnames

    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
     this
    -3.72
     only
    -3.39
     to
    -3.09
     from
    -2.94
     with
    -2.86
     at
    -2.84
     in
    -2.81
     every
    -2.78
     on
    -2.75
     when
    -2.58
    POSITIVE LOGITS
    -\\
    2.98
    romeda
    2.67
    皛
    2.53
    奁
    2.48
    lllll
    2.45
    -“
    2.45
    vereignty
    2.42
    alism
    2.42
    llten
    2.41
    vereign
    2.38
    Activations Density 15.406%

    No Known Activations