© 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. 1192
    Prev
    Next
    INDEX
    Explanations

    prediction vs actual

    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
     میلیارد
    -0.81
     資料
    -0.74
    señor
    -0.70
    Saison
    -0.70
    âge
    -0.67
    iempo
    -0.67
    subsec
    -0.66
     kuhusu
    -0.65
    jose
    -0.64
    roč
    -0.64
    POSITIVE LOGITS
     true
    1.52
     predicted
    1.51
    true
    1.46
     actual
    1.30
     truth
    1.28
     predictions
    1.26
     prediction
    1.25
    predicted
    1.19
     TRUE
    1.17
    真实
    1.16
    Activations Density 0.006%

    No Known Activations