© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22173
    Prev
    Next
    INDEX
    Explanations

    moving or handling physical objects

    np_acts-logits-general · gemini-2.5-flash-lite

    lifting objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     अल्फा
    0.43
    Ტ
    0.43
    нке
    0.41
     електрон
    0.39
     нулю
    0.39
     वृद्धा
    0.39
    tanh
    0.38
     ಪು
    0.38
    њу
    0.38
    ಇ
    0.38
    POSITIVE LOGITS
     czyli
    0.51
     odnosno
    0.46
    转移
    0.45
     transferring
    0.43
     یعنی
    0.43
    ابقة
    0.42
     transfer
    0.42
     motor
    0.42
     taşı
    0.42
     using
    0.41
    Activations Density 0.001%

    No Known Activations