© 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. 153583
    Prev
    Next
    INDEX
    Explanations

    non-english character recognition

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

    limited government and 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
     wrongs
    0.47
     Hamiltonian
    0.46
     entered
    0.46
     in
    0.45
    man
    0.44
    薪
    0.44
     editors
    0.44
     spent
    0.43
    entered
    0.43
     fluid
    0.43
    POSITIVE LOGITS
     нека
    0.57
     ރ
    0.56
     질
    0.55
     Йо
    0.55
    пусти
    0.52
    チャンス
    0.52
    ز
    0.51
     публі
    0.51
     якості
    0.50
     패
    0.50
    Activations Density 0.000%

    No Known Activations