© 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-16K
    7. 1958
    Prev
    Next
    INDEX
    Explanations

    appreciates that

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
        
    1.10
     Nut
    0.71
     NUT
    0.71
     contral
    0.67
     THAT
    0.64
    ALSO
    0.62
    oxal
    0.62
    utan
    0.62
     совме
    0.60
    勞
    0.59
    POSITIVE LOGITS
    GFR
    1.47
    isms
    1.38
    kira
    1.36
    ism
    1.36
    kins
    1.33
    izers
    1.33
    ISM
    1.32
    ismo
    1.29
    izability
    1.29
    ization
    1.28
    Activations Density 0.053%

    No Known Activations