© 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-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 39146
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns in Slavic and Germanic languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_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
    سي
    0.40
    Յ
    0.39
     descre
    0.37
    common
    0.36
    со
    0.36
     descon
    0.36
     आराधना
    0.36
     মায়
    0.36
    东北
    0.36
    ﾂ
    0.35
    POSITIVE LOGITS
     badly
    0.40
    veda
    0.38
     quietly
    0.38
     Buna
    0.37
     должны
    0.37
    也能
    0.37
     virkelig
    0.37
     poorly
    0.36
     сильно
    0.36
     possiamo
    0.36
    Activations Density 0.002%

    No Known Activations