© 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. 41151
    Prev
    Next
    INDEX
    Explanations

    expensive, losing, wasting

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

    magnets, attract, repel

    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
     Smiley
    0.51
    鎳
    0.50
    奶
    0.47
     почти
    0.45
     cigarette
    0.44
    杯
    0.44
    克
    0.43
    美
    0.43
     cig
    0.43
    艺术
    0.41
    POSITIVE LOGITS
    duration
    0.49
     acela
    0.47
    tbl
    0.44
    ázej
    0.44
     evacuate
    0.44
     formalin
    0.44
     unrelenting
    0.44
    lde
    0.44
    lose
    0.44
     preclude
    0.43
    Activations Density 0.000%

    No Known Activations