© 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. 242908
    Prev
    Next
    INDEX
    Explanations

    specifically, list, lost, authors, walls, cookies

    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
    ید
    0.53
    ницу
    0.46
    绁
    0.45
    ამართ
    0.44
    والفقار
    0.43
    цкий
    0.43
    ைக
    0.42
    cional
    0.42
    িকাল
    0.42
    یند
    0.41
    POSITIVE LOGITS
     таким
    0.49
    ú
    0.47
     поклон
    0.46
     см
    0.46
     проведен
    0.45
     проекти
    0.45
    І
    0.44
     сьогодні
    0.44
     بهذا
    0.44
     заря
    0.44
    Activations Density 0.000%

    No Known Activations