© 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. 86256
    Prev
    Next
    INDEX
    Explanations

    Jaitley

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

    dropping

    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
    乖
    0.49
     Quis
    0.48
    мас
    0.48
    хо
    0.46
    Ꮣ
    0.46
     Cousin
    0.44
     Kunde
    0.42
    才
    0.42
    ութ
    0.42
    出荷
    0.41
    POSITIVE LOGITS
    ^*\
    0.48
    อาหาร
    0.46
    يين
    0.46
     intervenir
    0.45
     নীতি
    0.44
    SII
    0.44
    ี้
    0.44
    toilet
    0.44
    ঢাকা
    0.44
    飯
    0.44
    Activations Density 0.000%

    No Known Activations