© 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. 13849
    Prev
    Next
    INDEX
    Explanations

    sha followed

    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
    ↵
    -3.02
    琑
    -2.73
     pero
    -2.73
     mistaken
    -2.48
    with
    -2.45
    팹
    -2.44
     ก็
    -2.41
    割と
    -2.41
     
    -2.39
    知らない
    -2.38
    POSITIVE LOGITS
    و
    2.63
    Ꭳ
    2.61
    ي
    2.59
    迳
    2.53
    *
    2.52
    臜
    2.45
    <
    2.38
    ſtra
    2.33
     nadru
    2.31
    贗
    2.31
    Activations Density 0.004%

    No Known Activations