© 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. 5034
    Prev
    Next
    INDEX
    Explanations

    uppercase and punctuation followed by words

    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
     illetve
    1.39
    َا
    1.39
     および
    1.27
     及び
    1.27
    および
    1.24
     desarrollando
    1.23
     источ
    1.23
     Сайт
    1.20
    ческими
    1.19
     이용하여
    1.19
    POSITIVE LOGITS
    !
    1.62
    .
    1.62
    .*
    1.60
     reckoned
    1.45
    everything
    1.44
    .•
    1.42
    *.
    1.41
    It
    1.32
    Back
    1.32
     everything
    1.30
    Activations Density 0.076%

    No Known Activations