© 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. 10-GEMMASCOPE-RES-131K
    7. 12865
    Prev
    Next
    INDEX
    Explanations

    am or pm time

    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_10/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
     anderer
    -1.57
     vorüber
    -1.46
     Fällen
    -1.34
     compartido
    -1.34
     autre
    -1.33
    一辆
    -1.32
     schmerz
    -1.30
     seventeen
    -1.30
     altres
    -1.29
     other
    -1.28
    POSITIVE LOGITS
     Если
    1.70
    kaç
    1.43
    izacja
    1.36
    很重要
    1.34
    是啊
    1.31
    每个
    1.31
    tists
    1.31
    〜
    1.30
    吗
    1.30
    此时
    1.29
    Activations Density 0.021%

    No Known Activations