© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4341
    Prev
    Next
    INDEX
    Explanations

    foreign grammatical particles and pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
     coisas
    2.32
    が変わ
    2.30
    が出
    2.24
    ченные
    2.22
    是对
    2.22
    がある
    2.21
    是个
    2.20
    ^{+},
    2.20
    をや
    2.19
    はある
    2.18
    POSITIVE LOGITS
     비롯
    1.26
     st
    1.25
     중심으로
    1.24
     enc
    1.17
     th
    1.12
     al
    1.07
     c
    1.06
     통한
    1.03
     위한
    1.02
     t
    1.02
    Activations Density 0.011%

    No Known Activations