© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48710
    Prev
    Next
    INDEX
    Explanations

    spatial reasoning, visual tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ንጥረ
    0.50
    Ĉ
    0.50
     quelque
    0.47
    ů
    0.46
    istema
    0.45
     Trebuie
    0.45
    𝚃
    0.45
     arrivent
    0.44
    ą
    0.43
    ⵄ
    0.43
    POSITIVE LOGITS
    時期
    0.46
     unsustainable
    0.44
     as
    0.43
     unemployment
    0.42
     legal
    0.42
     jobless
    0.40
     magist
    0.39
     unemployed
    0.39
     y
    0.38
     persisting
    0.38
    Activations Density 0.002%

    No Known Activations