© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 5090
    Prev
    Next
    INDEX
    Explanations

    xy-plane or voltage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    7
    1.39
    3
    1.36
    4
    1.26
    8
    1.17
    lands
    1.16
     связи
    1.15
     liga
    1.14
     Liga
    1.14
    ستم
    1.13
     собственности
    1.13
    POSITIVE LOGITS
     deliberations
    1.09
    בּ
    1.05
     /ˈ
    1.03
     참
    1.02
     PREC
    1.02
    כּ
    1.01
     eyeglasses
    1.01
    ᾿
    1.01
     grits
    0.99
     McNeil
    0.95
    Activations Density 0.034%

    No Known Activations