© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108370
    Prev
    Next
    INDEX
    Explanations

    actual vs expected

    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
    様が
    -0.89
    ensively
    -0.84
    Preheat
    -0.84
    первых
    -0.82
    issait
    -0.82
    ganu
    -0.81
    ικο
    -0.81
    ulously
    -0.80
    allan
    -0.79
    ள்
    -0.78
    POSITIVE LOGITS
     actual
    6.50
    actual
    5.47
    Actual
    5.22
     Actual
    4.97
    实际
    4.41
    ACTUAL
    4.22
     ACTUAL
    4.19
     actually
    3.72
    實際
    3.72
    実際の
    3.42
    Activations Density 0.126%

    No Known Activations