© 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. 216068
    Prev
    Next
    INDEX
    Explanations

    handle situations

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

    actions and abstract nouns

    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
    (""))
    0.43
    Ė
    0.43
    дзі
    0.42
    ಿಣ
    0.42
    roje
    0.42
     зарубе
    0.41
     verwend
    0.41
    Ა
    0.41
     Ә
    0.40
     이르
    0.40
    POSITIVE LOGITS
     gió
    0.52
     preachers
    0.50
     blasts
    0.49
     perder
    0.48
     champions
    0.47
    Ghosts
    0.47
     Controllers
    0.47
     mastect
    0.46
     aggressively
    0.46
     efficaces
    0.45
    Activations Density 0.001%

    No Known Activations