© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 63698
    Prev
    Next
    INDEX
    Explanations

    have been, will benefit, under cupboard

    np_acts-logits-general · gemini-2.5-flash-lite

    handles multi-task capability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Reload
    0.48
     Slowly
    0.48
    ',
    0.47
    Armor
    0.47
    '],
    0.45
    ăz
    0.45
    UTS
    0.44
     Bounty
    0.44
    铠
    0.44
    Outgoing
    0.44
    POSITIVE LOGITS
     pudieron
    0.52
    semos
    0.51
    iquement
    0.50
    ଯ
    0.50
     മാത്രമേ
    0.49
    viendo
    0.48
     terrest
    0.47
     puedan
    0.47
     tibi
    0.46
     determinant
    0.46
    Activations Density 0.000%

    No Known Activations