© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 3993
    Prev
    Next
    INDEX
    Explanations

    app or applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     剤
    0.62
     vésicules
    0.59
     riduzione
    0.58
     ـ
    0.57
    ፫
    0.57
    owneri
    0.57
    ulfanyl
    0.56
    fdPar
    0.55
     alterações
    0.55
     réduction
    0.55
    POSITIVE LOGITS
     App
    1.01
    App
    0.95
     Applications
    0.75
     Apps
    0.74
    in
    0.73
    0
    0.72
     APP
    0.71
     앱
    0.71
    app
    0.70
     app
    0.69
    Activations Density 0.007%

    No Known Activations