© 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. 41944
    Prev
    Next
    INDEX
    Explanations

    clone

    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
    s
    -3.89
    ஂ
    -2.97
     тази
    -2.47
    //{
    -2.34
    全都
    -2.25
    _{\
    -2.25
    ts
    -2.20
    
    -2.19
     questo
    -2.19
     are
    -2.19
    POSITIVE LOGITS
    カレンダー
    2.53
    [
    2.44
    ↵
    2.23
     但是
    2.17
     —
    2.13
    为例
    2.11
     busted
    2.11
     dalam
    2.06
    胸口
    2.05
    钮
    2.03
    Activations Density 0.005%

    No Known Activations