© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 22825
    Prev
    Next
    INDEX
    Explanations

    French reflexive verbs

    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_40_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
    ್ಣ
    0.39
    ு
    0.38
    춘
    0.38
     vielf
    0.38
     divergents
    0.37
    త్ర
    0.36
     Frü
    0.36
    主的
    0.36
    ǃ
    0.36
     disintegration
    0.35
    POSITIVE LOGITS
     mieux
    0.42
     হয়
    0.40
     Depos
    0.39
     regolare
    0.38
     يكون
    0.38
    ndo
    0.36
    appeal
    0.36
    hesive
    0.36
    ce
    0.36
    icial
    0.36
    Activations Density 0.001%

    No Known Activations