© 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. 40-GEMMASCOPE-2-RES-65K
    7. 48347
    Prev
    Next
    INDEX
    Explanations

    mobile app development

    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/layer_40_width_65k_l0_medium
    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
     principalColumn
    0.42
    Tensor
    0.39
    媟
    0.38
     mouseY
    0.38
    raž
    0.37
     encomendas
    0.37
    Grpc
    0.37
    WebGL
    0.36
    BOOLE
    0.36
    얄
    0.36
    POSITIVE LOGITS
    タップ
    0.53
     mobile
    0.44
     grades
    0.43
    filterable
    0.42
     mobiles
    0.39
     móviles
    0.39
    手机
    0.38
     ফোন
    0.38
    敗
    0.37
    ستگی
    0.37
    Activations Density 0.007%

    No Known Activations