© 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. 250432
    Prev
    Next
    INDEX
    Explanations

    targeted networks

    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
    増加
    0.50
    drunk
    0.49
     सैलरी
    0.46
    WordPress
    0.45
     نوش
    0.45
     बढ़त
    0.44
    保証
    0.44
    Notably
    0.43
    Méd
    0.42
    \}$.
    0.42
    POSITIVE LOGITS
     Somerville
    0.46
     unsightly
    0.45
     offen
    0.44
     extraneous
    0.44
     dép
    0.43
     occasionally
    0.43
     of
    0.43
    տ
    0.43
     adversely
    0.42
     inclement
    0.42
    Activations Density 0.001%

    No Known Activations