© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 171878
    Prev
    Next
    INDEX
    Explanations

    phrases like "not have", "such a"

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

    existence, illegal, errors, crisis

    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
    Negative Logits
    โรค
    0.54
    瞌
    0.53
    蒺
    0.51
    ohyd
    0.50
    乸
    0.49
    阏
    0.49
    Closure
    0.48
    Besch
    0.48
    Geocoder
    0.48
    贛
    0.48
    POSITIVE LOGITS
     ২৭
    0.49
     fundo
    0.47
     admiring
    0.47
     thirty
    0.43
     Caledonia
    0.43
     admired
    0.43
     skl
    0.43
    lp
    0.43
     wager
    0.43
     Swimming
    0.43
    Activations Density 0.000%

    No Known Activations