© 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-65K
    7. 61009
    Prev
    Next
    INDEX
    Explanations

    plot y-axis labels

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    辩
    0.43
     নিয়ন্ত্র
    0.43
     stabilise
    0.42
     maths
    0.41
    Divider
    0.41
    нуться
    0.41
    に対し
    0.40
    யின்
    0.40
     полез
    0.40
     Divider
    0.40
    POSITIVE LOGITS
     exclusivamente
    0.43
    အ
    0.41
     degli
    0.40
    in
    0.38
    agg
    0.38
    abras
    0.38
    uri
    0.37
     Landry
    0.37
     τῶν
    0.37
    at
    0.36
    Activations Density 0.014%

    No Known Activations