© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 202750
    Prev
    Next
    INDEX
    Explanations

    Vishnu, data, healing

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

    after 'the'

    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
    Not in Any Lists

    No Comments

    Negative Logits
     इलेक्ट्र
    0.42
    ares
    0.41
     ইলেকট্র
    0.40
     Electronics
    0.39
     losers
    0.39
     electronics
    0.39
    Electronics
    0.39
     或
    0.39
     Ung
    0.38
     或者
    0.38
    POSITIVE LOGITS
     воздей
    0.51
    വി
    0.50
     dès
    0.49
     efet
    0.47
    தொ
    0.47
    يش
    0.46
     растение
    0.46
     rê
    0.45
    Dü
    0.45
    శ
    0.44
    Activations Density 0.000%

    No Known Activations