© 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. 129121
    Prev
    Next
    INDEX
    Explanations

    your child

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

    subject-verb agreement

    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
     συνέχ
    0.45
     Mujhe
    0.44
     яхшы
    0.42
    떳
    0.42
     รู้
    0.41
    tgts
    0.41
     segí
    0.41
    lblName
    0.41
     kiedy
    0.41
     Businessman
    0.41
    POSITIVE LOGITS
    ING
    0.52
     corresponding
    0.52
    ing
    0.48
     peppermint
    0.48
    O
    0.47
    Leaving
    0.45
     external
    0.45
    을
    0.44
    P
    0.43
     rosette
    0.43
    Activations Density 0.001%

    No Known Activations