© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45294
    Prev
    Next
    INDEX
    Explanations

    making something worse

    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
    很棒
    -2.59
    D
    -2.58
    seems
    -2.52
    ㈮
    -2.48
     feuer
    -2.47
     remnants
    -2.42
    referred
    -2.41
    ti
    -2.41
    厹
    -2.36
    (
    -2.33
    POSITIVE LOGITS
    ～。
    2.88
     and
    2.30
    ↵
    2.30
     Diese
    2.23
     način
    2.14
    ～！
    2.13
     хто
    2.08
    してみました
    2.03
    ｗｗｗ
    1.99
     Not
    1.98
    Activations Density 0.004%

    No Known Activations