© 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. 198685
    Prev
    Next
    INDEX
    Explanations

    financial institutions, or fundraising

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

    initial steps

    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
     N
    0.56
     Najib
    0.54
     C
    0.47
     western
    0.47
    A
    0.45
     androidx
    0.44
    western
    0.44
     Nau
    0.44
     Ni
    0.43
     Colby
    0.42
    POSITIVE LOGITS
     êtres
    0.50
     scandals
    0.48
     surpluses
    0.47
    ون
    0.47
    隽
    0.47
     ghế
    0.47
    毌
    0.47
    वेशन
    0.46
    ließt
    0.46
    㗆
    0.46
    Activations Density 0.001%

    No Known Activations