© 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. 50638
    Prev
    Next
    INDEX
    Explanations

    world of

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

    calculating time

    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
     parturient
    0.48
     blooms
    0.47
     arcs
    0.47
    িত্যক্ত
    0.45
    िमम
    0.43
    amazaki
    0.43
    6
    0.42
     persists
    0.42
    ')";
    0.42
     elevates
    0.41
    POSITIVE LOGITS
     egent
    0.47
     veter
    0.45
    스는
    0.45
    実は
    0.43
    䚺
    0.43
    ભ
    0.43
     stru
    0.42
     واح
    0.42
     lím
    0.41
    teis
    0.41
    Activations Density 0.000%

    No Known Activations