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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 219
    Prev
    Next
    INDEX
    Explanations

    Russian prefixes like пре- and verbs like образовывать

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

    Habilidad, precious

    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_16k_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
    +
    0.17
    essional
    0.16
     numérique
    0.14
     للنساء
    0.14
    y
    0.14
     walkable
    0.13
     کرنے
    0.13
     banget
    0.13
     lackluster
    0.13
     rodeo
    0.13
    POSITIVE LOGITS
    اید
    0.14
    前記
    0.14
    Efter
    0.14
    新たに
    0.14
    د
    0.14
    न्ही
    0.13
    頔
    0.13
    謂
    0.12
    Peng
    0.12
    ዘጋ
    0.12
    Activations Density 0.553%

    No Known Activations