© 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. 39312
    Prev
    Next
    INDEX
    Explanations

    introduction and beginnings

    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
     you
    -1.76
    {
    -1.43
    enschappe
    -1.23
    
    -1.23
    Isn
    -1.22
     obr
    -1.20
    CAMP
    -1.20
    already
    -1.19
    verhältnis
    -1.18
    currently
    -1.17
    POSITIVE LOGITS
     thậm
    1.49
    引言
    1.38
    忸
    1.34
    きっかけ
    1.33
    Характеристики
    1.32
    ロ
    1.32
     five
    1.31
     joyas
    1.30
    Итог
    1.27
    после
    1.27
    Activations Density 0.045%

    No Known Activations