© 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. 42592
    Prev
    Next
    INDEX
    Explanations

    Kaz names and places

    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
    身边的
    -3.00
     resourceful
    -2.80
     crafty
    -2.66
    髕
    -2.64
    诹
    -2.53
    宬
    -2.52
    还想
    -2.50
    ୌ
    -2.42
     laborious
    -2.39
     alemanes
    -2.39
    POSITIVE LOGITS
    {
    3.55
    </sup>
    2.70
    and
    2.64
    __':
    
    2.45
    of
    2.44
    to
    2.36
    e
    2.25
    蔼
    2.22
    over
    2.16
    er
    2.13
    Activations Density 0.003%

    No Known Activations