© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12063
    Prev
    Next
    INDEX
    Explanations

    Russian past tense verb byla

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    ilit
    1.26
     PERSON
    1.18
     ૩
    1.11
     persons
    1.10
    ilie
    1.07
    pear
    1.06
    abstraction
    1.06
    ritual
    1.05
    opening
    1.05
     ٣
    1.04
    POSITIVE LOGITS
     quase
    1.49
     semuanya
    1.43
     xwe
    1.37
     divent
    1.37
     magnifique
    1.34
     súa
    1.34
     všechny
    1.34
     bijna
    1.33
     semelhantes
    1.32
     nombreux
    1.32
    Activations Density 0.000%

    No Known Activations