© 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. 229744
    Prev
    Next
    INDEX
    Explanations

    bowl below

    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
     verses
    0.52
    راہ
    0.52
    軛
    0.50
    andas
    0.49
     mutu
    0.49
     pradesh
    0.49
     There
    0.49
     मृत्यु
    0.49
    ach
    0.48
     பகு
    0.48
    POSITIVE LOGITS
    ↵
    0.48
    লাম
    0.43
    BuildContext
    0.42
    ので
    0.42
     Lamont
    0.40
    HomePage
    0.40
     domác
    0.39
    饪
    0.39
    крови
    0.39
    iftoire
    0.39
    Activations Density 0.001%

    No Known Activations