© 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. 48574
    Prev
    Next
    INDEX
    Explanations

    chess championship titles

    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
    King
    -0.90
    تام
    -0.82
    王
    -0.79
    Olymp
    -0.73
    Semitic
    -0.72
    Amerika
    -0.71
    alık
    -0.71
     Olymp
    -0.71
     רב
    -0.71
    Poly
    -0.70
    POSITIVE LOGITS
    ndal
    0.86
    citename
    0.79
    atism
    0.75
    тения
    0.75
     ਅ
    0.74
    鲶
    0.74
    沌
    0.73
    ">//
    0.73
    だからこそ
    0.71
    latego
    0.71
    Activations Density 0.007%

    No Known Activations