© 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. 51389
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and referential words

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

    tell me:

    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
     लागि
    0.54
     terhadap
    0.47
     เหมือน
    0.44
    ให้กับ
    0.42
     élarg
    0.42
    กับ
    0.41
    จากการ
    0.41
    ′-
    0.41
     dàng
    0.41
     erad
    0.40
    POSITIVE LOGITS
     they
    0.54
     bienvenidos
    0.52
     something
    0.51
     we
    0.51
    aii
    0.46
     času
    0.45
    you
    0.45
    something
    0.44
     cosas
    0.44
     you
    0.43
    Activations Density 0.035%

    No Known Activations