© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 12183
    Prev
    Next
    INDEX
    Explanations

    possessive relative pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    าร์
    1.00
    Ultimately
    0.97
    ًا
    0.92
     Ultimately
    0.92
    ers
    0.92
    !
    0.91
    '
    0.89
    Ī
    0.89
     Deci
    0.88
    Flex
    0.87
    POSITIVE LOGITS
     которая
    1.38
     cuya
    1.36
     která
    1.34
     التي
    1.32
     cuyo
    1.29
     cuja
    1.28
    whose
    1.25
     whose
    1.25
     které
    1.24
     waarvan
    1.22
    Activations Density 0.053%

    No Known Activations