© 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. 83292
    Prev
    Next
    INDEX
    Explanations

    shutout and seven innings

    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
    Forty
    -0.83
    pshots
    -0.81
     Forty
    -0.80
    ־ה
    -0.77
    していない
    -0.75
    ਢ
    -0.74
    是怎么回事
    -0.74
    assi
    -0.73
    ひと
    -0.71
     Thirty
    -0.70
    POSITIVE LOGITS
     shutout
    1.38
     seven
    1.10
    Shut
    1.07
     shut
    1.06
     Shut
    1.06
    SHUT
    0.99
     complete
    0.95
     six
    0.91
     five
    0.90
     SHUT
    0.90
    Activations Density 0.018%

    No Known Activations