© 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. 7263
    Prev
    Next
    INDEX
    Explanations

    proposing or stating something

    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
     könnt
    -1.59
    平日
    -1.53
     y
    -1.52
     He
    -1.51
     تلك
    -1.49
     (
    -1.49
    arraycopy
    -1.49
     dont
    -1.48
     下
    -1.46
     You
    -1.45
    POSITIVE LOGITS
    鹮
    1.78
     薬局
    1.73
    糺
    1.70
    関連リンク
    1.67
    ፒ
    1.66
    そりゃ
    1.59
     künftig
    1.56
     内衣
    1.56
    錾
    1.55
    jątk
    1.54
    Activations Density 0.005%

    No Known Activations