© 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. 15316
    Prev
    Next
    INDEX
    Explanations

    adv

    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
    .“
    -2.45
    玕
    -2.42
     sodass
    -2.42
    」、「
    -2.39
     wodurch
    -2.39
     ‘’
    -2.34
    …」
    -2.30
     ”
    -2.28
    Ꮞ
    -2.27
    前世
    -2.23
    POSITIVE LOGITS
    s
    2.97
    躋
    2.70
     "
    2.64
    跻
    2.63
    !"
    2.53
    你
    2.44
    if
    2.42
     soportar
    2.39
    我們
    2.23
     potřeb
    2.22
    Activations Density 0.002%

    No Known Activations