© 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. 192633
    Prev
    Next
    INDEX
    Explanations

    longitudinal axis, Kindergarten (JK), I forgot

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

    self followed by dot

    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
    MARKS
    0.51
    DESIGN
    0.50
    下
    0.49
    notifications
    0.48
    կ
    0.47
    ас
    0.47
     blessings
    0.46
    ﺳ
    0.46
     DESIGN
    0.46
    design
    0.46
    POSITIVE LOGITS
     erlaub
    0.51
     มุม
    0.50
     yüzden
    0.47
     antisemit
    0.47
     varietà
    0.46
     pü
    0.46
     deaktiv
    0.46
     komponen
    0.46
     dynast
    0.46
    eonium
    0.45
    Activations Density 0.000%

    No Known Activations