© 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. 5118
    Prev
    Next
    INDEX
    Explanations

    text and code structure

    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
     furono
    1.00
    就是在
    0.94
    是他
    0.89
     hia
    0.89
    läuft
    0.87
     finns
    0.86
    =
    0.86
    )=(
    0.79
    (&
    0.78
    就是
    0.78
    POSITIVE LOGITS
     generally
    1.82
    generally
    1.79
     tetrachloride
    1.77
     carboxyl
    1.76
    Require
    1.76
    туре
    1.75
     pij
    1.74
     inherently
    1.73
     monatomic
    1.73
     Lipschitz
    1.70
    Activations Density 0.019%

    No Known Activations