© 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. 209706
    Prev
    Next
    INDEX
    Explanations

    academic or publisher names

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

    governing regulations

    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
     連
    0.66
     transform
    0.50
     根据
    0.49
     গোল
    0.49
     vanish
    0.48
     我們
    0.48
     የማይ
    0.47
     degrade
    0.46
     aligned
    0.46
     对
    0.46
    POSITIVE LOGITS
     intereses
    0.48
    چم
    0.47
    Herkese
    0.45
    وْ
    0.45
     Estonia
    0.45
    하였습니다
    0.44
    했습니다
    0.44
    itudine
    0.44
     organes
    0.44
     ejemplos
    0.42
    Activations Density 0.000%

    No Known Activations