© 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. 145252
    Prev
    Next
    INDEX
    Explanations

    distant past, ADA advertising, System Information, sea lion pups

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

    abbreviations and specific names

    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
     рождения
    0.55
     структур
    0.51
    ر
    0.50
    ເພດ
    0.45
     нього
    0.45
    rieben
    0.45
    াভাবিক
    0.44
    にした
    0.44
    parametrize
    0.44
     nghiệm
    0.44
    POSITIVE LOGITS
     മത്സ്യ
    0.48
    stin
    0.45
     Hask
    0.45
    undu
    0.44
     pon
    0.44
    ハリ
    0.44
     Summary
    0.43
    近
    0.43
     Utica
    0.43
     adidas
    0.43
    Activations Density 0.001%

    No Known Activations