© 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. 71771
    Prev
    Next
    INDEX
    Explanations

    sentence endings punctuation

    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
    1
    -3.28
    If
    -3.13
    from
    -3.00
    3
    -2.97
    2
    -2.94
    5
    -2.91
    鏵
    -2.81
    鬭
    -2.77
    8
    -2.72
    7
    -2.72
    POSITIVE LOGITS
    ↵
    2.84
    と言われる
    2.80
    翃
    2.70
    抽出
    2.56
    淬
    2.55
    褥
    2.50
    茗
    2.48
    拇
    2.47
    。“
    2.44
     It
    2.42
    Activations Density 0.003%

    No Known Activations