© 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. 40-GEMMASCOPE-2-RES-262K
    7. 221575
    Prev
    Next
    INDEX
    Explanations

    reflexes and followed by infinitives

    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
    compression
    0.46
    ktops
    0.41
     प्रचलित
    0.41
    榱
    0.41
     Função
    0.39
    壓縮
    0.39
    strcmp
    0.39
     অর্থাৎ
    0.39
    況
    0.39
    厸
    0.39
    POSITIVE LOGITS
     +(
    0.49
     refleks
    0.46
     reflex
    0.46
     followed
    0.45
     Reflex
    0.44
     reflexes
    0.42
    followed
    0.41
     فارس
    0.41
     crops
    0.41
     minded
    0.40
    Activations Density 0.035%

    No Known Activations