© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12531
    Prev
    Next
    INDEX
    Explanations

    relating entities to action or direction

    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_31_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
    ov
    0.53
    自分が
    0.50
    自己的
    0.50
    read
    0.48
     Interchange
    0.46
    自分の
    0.44
    自己
    0.44
    h
    0.44
    om
    0.43
    op
    0.43
    POSITIVE LOGITS
     deewana
    0.61
     into
    0.50
     إلى
    0.50
     toward
    0.49
     unscathed
    0.49
     complacent
    0.48
     weary
    0.47
    へと
    0.47
     vào
    0.46
     irresist
    0.46
    Activations Density 0.088%

    No Known Activations