© 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. 75852
    Prev
    Next
    INDEX
    Explanations

    Bloomberg Television OR street food

    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
    ле
    0.50
    -
    0.46
     extremities
    0.46
    AIN
    0.45
    ↵
    0.45
    ↵↵
    0.45
     invertebrate
    0.44
     regions
    0.44
     јо
    0.43
    癒
    0.43
    POSITIVE LOGITS
    🧙
    0.51
     laughable
    0.50
     hakkında
    0.49
     Necklace
    0.48
    یدی
    0.48
    🧶
    0.48
    ንዳንድ
    0.47
     NavBar
    0.47
     LinkedIn
    0.46
     désormais
    0.46
    Activations Density 0.548%

    No Known Activations