© 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. 34762
    Prev
    Next
    INDEX
    Explanations

    language learning apps

    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
     Erik
    0.40
     Mün
    0.39
     సాహిత
    0.37
    Erik
    0.37
     accompaniment
    0.36
    아이
    0.36
    Мушко
    0.35
     (£
    0.35
    Dak
    0.35
    خان
    0.35
    POSITIVE LOGITS
     apps
    2.27
     Apps
    1.96
     app
    1.93
    アプリ
    1.91
    apps
    1.90
    Apps
    1.79
     앱
    1.78
     ऐप्स
    1.63
    앱
    1.60
     aplicativos
    1.58
    Activations Density 0.002%

    No Known Activations