© 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. 235261
    Prev
    Next
    INDEX
    Explanations

    many things

    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
    má
    0.53
     élargies
    0.50
    setosa
    0.47
    chyné
    0.47
    बिया
    0.43
    Ꭾ
    0.42
     aquello
    0.42
    maid
    0.41
    êmica
    0.41
    پے
    0.41
    POSITIVE LOGITS
     SOB
    0.49
    डेड
    0.48
     indefin
    0.48
     ODM
    0.48
     fuelled
    0.48
     СССР
    0.47
     SECOND
    0.47
     totally
    0.46
    𝑺
    0.46
     sna
    0.46
    Activations Density 0.001%

    No Known Activations