© 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. 193896
    Prev
    Next
    INDEX
    Explanations

    final results

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

    processed strings, energy wave

    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
     ushered
    0.51
     우리의
    0.51
     seharusnya
    0.46
    ン
    0.46
     siang
    0.45
     churches
    0.45
     كبيرة
    0.45
    企業の
    0.45
    攏
    0.45
     picnics
    0.44
    POSITIVE LOGITS
    ident
    0.48
    ▀
    0.47
    éna
    0.46
    tra
    0.46
    dele
    0.46
    fant
    0.46
    Point
    0.45
    腎
    0.45
    禁
    0.44
    ─
    0.43
    Activations Density 0.000%

    No Known Activations