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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 12173
    Prev
    Next
    INDEX
    Explanations

    sports games and fixtures

    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
    思議
    -0.81
    大地
    -0.76
    idać
    -0.75
    ลา
    -0.74
    scored
    -0.73
     scored
    -0.73
    Ἅ
    -0.72
     Score
    -0.71
    打
    -0.70
     ギャ
    -0.70
    POSITIVE LOGITS
     fixture
    1.24
     fixtures
    1.15
     Fixture
    1.06
    fixtures
    0.94
    fixture
    0.93
    Fixture
    0.89
     pencil
    0.88
     Fixtures
    0.88
     rearranged
    0.87
    Fixtures
    0.85
    Activations Density 0.030%

    No Known Activations