© 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. 207829
    Prev
    Next
    INDEX
    Explanations

    and treatment

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

    dates and specific entities

    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
    ynit
    0.50
     francés
    0.50
    inicio
    0.50
    lb
    0.47
    indeed
    0.46
    thread
    0.46
     rehabilitate
    0.46
     conceivably
    0.45
     capacit
    0.45
    "}}
    0.45
    POSITIVE LOGITS
    Reviews
    0.48
    ط
    0.47
    ాత్రి
    0.44
    امر
    0.43
    莺
    0.43
    貅
    0.43
    徇
    0.43
    یان
    0.43
     Vectors
    0.43
    窸
    0.43
    Activations Density 0.006%

    No Known Activations