© 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. 109670
    Prev
    Next
    INDEX
    Explanations

    place names and entities

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

    Seongsan Ilchulbong, loophole, Ring, potentially

    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
    t
    0.69
    a
    0.68
    f
    0.60
    st
    0.54
    tt
    0.54
    r
    0.54
    controller
    0.54
    o
    0.53
    sk
    0.52
    pa
    0.52
    POSITIVE LOGITS
    択
    0.57
     미래
    0.51
     그러면은
    0.50
    티
    0.49
     haies
    0.49
     تصمیم
    0.48
     социально
    0.48
     의견
    0.48
     komunik
    0.48
    나는
    0.48
    Activations Density 0.001%

    No Known Activations