© 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. 83298
    Prev
    Next
    INDEX
    Explanations

    correct or incorrect statements

    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
     nyky
    -0.88
    uszcz
    -0.82
    ॐ
    -0.79
    Perfect
    -0.78
    River
    -0.77
    با
    -0.77
    yalar
    -0.77
    siga
    -0.77
    Friday
    -0.75
    lobe
    -0.74
    POSITIVE LOGITS
     right
    6.28
     correct
    3.95
    right
    3.75
    Right
    3.55
     Right
    3.42
     RIGHT
    3.14
    RIGHT
    2.97
    correct
    2.56
     đúng
    2.44
     wrong
    2.39
    Activations Density 0.032%

    No Known Activations