© 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. 186055
    Prev
    Next
    INDEX
    Explanations

    business, financial, history, jail, Bowl

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

    tongue twisters

    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
    οδο
    0.52
     succinct
    0.46
    ivado
    0.46
     доклад
    0.46
    ῴ
    0.45
     micelles
    0.44
    มนเชสเตอร์
    0.44
     unfolded
    0.44
     απ
    0.44
    шать
    0.43
    POSITIVE LOGITS
    t
    0.64
    ský
    0.52
    o
    0.50
    다가
    0.48
     Bande
    0.47
    prime
    0.46
    RW
    0.46
    test
    0.46
    olphe
    0.45
     次
    0.45
    Activations Density 0.001%

    No Known Activations