© 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. 56718
    Prev
    Next
    INDEX
    Explanations

    size differencesevolving information

    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
    NYC
    0.42
    Persistent
    0.42
    }}$;
    0.41
     Persistent
    0.41
     paisajes
    0.41
    plikasi
    0.41
    Many
    0.40
     arenas
    0.40
     juguetes
    0.40
    酷
    0.40
    POSITIVE LOGITS
    ())
    0.45
     unite
    0.45
     endorse
    0.44
     validate
    0.44
     ク
    0.44
     rende
    0.44
    鹽
    0.43
     permite
    0.43
     guarantor
    0.43
     島
    0.42
    Activations Density 0.004%

    No Known Activations