© 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. 14011
    Prev
    Next
    INDEX
    Explanations

    completion of actions

    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
     gustado
    -1.64
    руя
    -1.54
    Ⓧ
    -1.54
    咴
    -1.54
     allows
    -1.53
    螽
    -1.51
    祘
    -1.46
    㐂
    -1.45
    倧
    -1.42
     تجمعات
    -1.41
    POSITIVE LOGITS
    勿論
    1.30
    铤
    1.29
     .
    1.29
    たまた
    1.26
    níků
    1.23
     Damn
    1.23
    前来
    1.23
     ต
    1.22
    驚き
    1.21
    报表
    1.21
    Activations Density 0.025%

    No Known Activations