© 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. 7-GEMMASCOPE-2-RES-16K
    7. 10844
    Prev
    Next
    INDEX
    Explanations

    internal states after reflexive pronouns

    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_7_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
    ূট
    2.40
    た
    2.23
    eltic
    1.90
    퍼
    1.87
    ript
    1.84
    딴
    1.84
    ণু
    1.83
    ్రహ
    1.82
    ുകളും
    1.81
    IVIDUAL
    1.81
    POSITIVE LOGITS
    urge
    2.20
     déb
    2.14
    قبال
    2.13
    yy
    2.08
    y
    2.07
    lok
    2.04
    litz
    1.99
    l
    1.95
    lift
    1.95
    ০
    1.94
    Activations Density 0.018%

    No Known Activations