© 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. 246033
    Prev
    Next
    INDEX
    Explanations

    Yemi Osinbajo

    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
    ાળ
    0.53
     документов
    0.50
    πει
    0.49
     Opinions
    0.47
    bagai
    0.47
    ௐ
    0.46
     आपात
    0.45
     Podium
    0.45
    ერ
    0.45
    ਪ
    0.44
    POSITIVE LOGITS
     underval
    0.48
    -\
    0.46
     مق
    0.45
    Tambah
    0.45
     いっ
    0.44
    heran
    0.44
     معنات
    0.43
     crevices
    0.43
    maintain
    0.43
    źdz
    0.43
    Activations Density 0.001%

    No Known Activations