© 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. 49770
    Prev
    Next
    INDEX
    Explanations

    moving pattern yes

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

    game, fps, design, Rp, registered, control

    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
     of
    0.55
    ม
    0.50
    of
    0.48
    acji
    0.48
     aluminum
    0.47
    TO
    0.47
    X
    0.46
    IS
    0.46
     attorney
    0.46
    เพื่อ
    0.45
    POSITIVE LOGITS
    कॉइन
    0.47
    内心
    0.47
    دايه
    0.46
    ivent
    0.44
     TComponent
    0.44
    ंबित
    0.44
     হাসপাত
    0.43
    ртов
    0.43
    尼亚克
    0.42
    cPix
    0.42
    Activations Density 0.000%

    No Known Activations