© 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. 117686
    Prev
    Next
    INDEX
    Explanations

    business wire announcements

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

    first position tracking repeat

    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
     Yıld
    0.50
     Hör
    0.49
    体の
    0.46
     Pal
    0.45
    嫚
    0.44
    ódromo
    0.44
     ব্যান্ড
    0.44
     Flicker
    0.43
     निर्देशांक
    0.43
    ")],
    0.43
    POSITIVE LOGITS
    ren
    0.56
    to
    0.54
    final
    0.51
    loving
    0.51
    vi
    0.50
    it
    0.50
    projects
    0.49
    end
    0.48
    should
    0.47
    if
    0.46
    Activations Density 0.001%

    No Known Activations