© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31638
    Prev
    Next
    INDEX
    Explanations

    value, class, look, name, levels, graphical, density, durability

    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_34/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
    花的
    -0.84
    
    -0.79
    主演
    -0.77
     kunna
    -0.75
    Interceptor
    -0.75
    мирование
    -0.75
    ช่วง
    -0.73
    istir
    -0.72
    gerea
    -0.72
    リーツ
    -0.72
    POSITIVE LOGITS
    を持つ
    1.31
     sahip
    1.30
    의
    1.27
    ű
    1.13
     having
    1.05
     possessing
    1.04
     boasted
    1.04
    டைய
    1.04
     கொ
    0.98
     boasting
    0.98
    Activations Density 0.009%

    No Known Activations