© 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. 14111
    Prev
    Next
    INDEX
    Explanations

    boxing and combat sports

    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
     that
    -1.46
    
    -1.34
    “
    -1.27
     fahr
    -1.25
    T
    -1.23
     داخ
    -1.21
     ジュニア
    -1.20
    
    -1.20
    讓你
    -1.20
    why
    -1.20
    POSITIVE LOGITS
    vação
    1.28
    Nép
    1.15
    崛起
    1.11
    Before
    1.10
    zyści
    1.09
    Sự
    1.09
     kämpfen
    1.09
    isation
    1.08
     även
    1.06
    After
    1.05
    Activations Density 0.075%

    No Known Activations