© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 10944
    Prev
    Next
    INDEX
    Explanations

    possessive roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    you
    0.64
     you
    0.63
    𝚏
    0.62
     você
    0.59
     Microsoft
    0.59
     a
    0.57
     Pinch
    0.56
     Bull
    0.56
     ت
    0.55
    ppets
    0.55
    POSITIVE LOGITS
    自身の
    0.63
    自身的
    0.59
     തന്റെ
    0.57
     svoju
    0.56
     insofar
    0.56
    체의
    0.56
    வரின்
    0.56
     vasculature
    0.56
     자신의
    0.54
    自己的
    0.53
    Activations Density 0.034%

    No Known Activations