© 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. 232589
    Prev
    Next
    INDEX
    Explanations

    deeds, loans, emails

    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
    average
    0.49
    rotated
    0.48
     t
    0.47
     As
    0.46
    rhe
    0.45
    n
    0.45
    r
    0.45
     n
    0.44
    extreme
    0.44
     revolved
    0.44
    POSITIVE LOGITS
     deeds
    0.55
    ,​
    0.50
     seventies
    0.48
    ¹,
    0.47
     −/−
    0.47
     gelişmeler
    0.45
    ,$$
    0.45
    $,
    0.45
     Deeds
    0.44
     využ
    0.44
    Activations Density 0.004%

    No Known Activations