© 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. 107085
    Prev
    Next
    INDEX
    Explanations

    sports coaching and athletic development

    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
     föres
    -0.83
    PKT
    -0.79
    お疲れ
    -0.75
    ]",
    -0.73
     intracranial
    -0.73
    افية
    -0.72
     SIZES
    -0.72
    説明書
    -0.71
    tosa
    -0.71
    Вам
    -0.71
    POSITIVE LOGITS
     performance
    1.76
     elite
    1.60
     Performance
    1.59
    elite
    1.48
     High
    1.47
     Elite
    1.46
    Performance
    1.45
     coaching
    1.38
     Leistungs
    1.34
    High
    1.28
    Activations Density 0.040%

    No Known Activations