© 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. 218040
    Prev
    Next
    INDEX
    Explanations

    Isaiah who

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

    asking questions about purpose

    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
    ੋ
    0.53
    ↵
    0.49
    uploaded
    0.49
    Children
    0.48
    Uploaded
    0.47
    infected
    0.46
     Cian
    0.45
    CBD
    0.45
    ρας
    0.44
    infested
    0.44
    POSITIVE LOGITS
     äh
    0.51
     ఎక్కువగా
    0.49
     كه
    0.48
     meriye
    0.48
     dön
    0.48
    --");
    0.47
     designado
    0.47
     yoktur
    0.47
     ön
    0.46
     که
    0.46
    Activations Density 0.000%

    No Known Activations