© 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. 129255
    Prev
    Next
    INDEX
    Explanations

    PopupController, PopupDiv, Popup

    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
     stumbling
    -2.63
     می‌گوید
    -2.25
    蘗
    -2.22
    糴
    -2.20
    齙
    -2.13
    きは
    -2.09
     garganta
    -2.06
     saada
    -2.06
     інші
    -2.06
     некоторые
    -2.06
    POSITIVE LOGITS
    s
    3.89
    鹮
    3.34
    i
    3.05
    י
    2.84
    ്
    2.73
    乆
    2.69
    a
    2.63
    寕
    2.58
    ी
    2.58
    ي
    2.47
    Activations Density 0.005%

    No Known Activations