© 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. 10-GEMMASCOPE-RES-131K
    7. 100336
    Prev
    Next
    INDEX
    Explanations

    breathable

    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
     
    -2.77
     the
    -2.47
    𖣔
    -2.36
     `
    -2.33
     Now
    -2.20
     For
    -2.14
     Choosing
    -2.11
     เมื่อ
    -2.11
     When
    -2.09
     quando
    -2.09
    POSITIVE LOGITS
     成人
    2.23
    歃
    2.20
     تعدى
    2.17
     美食
    2.14
     艺术
    2.11
     技
    2.08
    стреча
    2.03
     marino
    2.03
    ydın
    2.02
     Carro
    2.00
    Activations Density 0.003%

    No Known Activations