© 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. 241590
    Prev
    Next
    INDEX
    Explanations

    mystery and unknowns

    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
    sk
    0.55
    th
    0.53
    sin
    0.51
    sa
    0.50
    o
    0.50
    st
    0.48
    sim
    0.47
    no
    0.46
    sm
    0.46
    stil
    0.46
    POSITIVE LOGITS
    謎
    0.53
    लट
    0.51
    ી
    0.48
     دیگر
    0.48
    یط
    0.48
    рата
    0.46
    ヤー
    0.46
     mysteries
    0.46
     исключительно
    0.45
     mystery
    0.44
    Activations Density 0.004%

    No Known Activations