© 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. 40-GEMMASCOPE-2-RES-262K
    7. 26092
    Prev
    Next
    INDEX
    Explanations

    above sea level

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Ix
    0.43
     ञ
    0.41
    icat
    0.40
     grueso
    0.38
    ouk
    0.37
    MaxSize
    0.37
     Casimir
    0.36
     తిరిగి
    0.36
    آ
    0.36
    diox
    0.36
    POSITIVE LOGITS
     above
    0.91
    above
    0.75
    Above
    0.75
     Above
    0.74
     ABOVE
    0.68
     acima
    0.67
     فوق
    0.62
     sopra
    0.61
     выше
    0.57
     boven
    0.56
    Activations Density 0.013%

    No Known Activations