© 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. 29063
    Prev
    Next
    INDEX
    Explanations

    and then actions

    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
     it
    -2.31
    によく
    -2.00
    에는
    -1.97
     często
    -1.97
    iaceae
    -1.92
     elevate
    -1.92
    そも
    -1.87
    ৄ
    -1.85
     bardziej
    -1.85
    おは
    -1.85
    POSITIVE LOGITS
     and
    2.67
     be
    2.33
     København
    1.96
    5
    1.89
    Américaine
    1.87
    咐
    1.83
    There
    1.83
    क्स
    1.80
    !
    1.80
     Если
    1.78
    Activations Density 0.314%

    No Known Activations