© 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. 10471
    Prev
    Next
    INDEX
    Explanations

    pushing and forces

    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
     murdered
    0.43
    馇
    0.42
     CustB
    0.42
    श्वर
    0.41
    ベージュ
    0.41
    шении
    0.41
    顧客
    0.41
     Administração
    0.41
     ভালোবাস
    0.41
    ད
    0.41
    POSITIVE LOGITS
     propulsion
    0.84
     propel
    0.77
     propelling
    0.72
     추진
    0.68
    推动
    0.62
    push
    0.61
     friction
    0.61
     pushing
    0.61
     propelled
    0.61
    力的
    0.60
    Activations Density 0.050%

    No Known Activations