© 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. 232321
    Prev
    Next
    INDEX
    Explanations

    not possible

    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
    了这个
    0.52
    ۵
    0.51
     каждого
    0.50
     знать
    0.49
     алфа
    0.48
    ᱕
    0.47
    创立
    0.46
    5
    0.46
    一下子
    0.45
    들의
    0.45
    POSITIVE LOGITS
     geranium
    0.44
     quinine
    0.43
     condensers
    0.43
     embolism
    0.42
    ولة
    0.42
     marble
    0.42
     पाण्या
    0.42
     ouvrage
    0.41
     subside
    0.41
     ponds
    0.41
    Activations Density 0.000%

    No Known Activations