© 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. 31-GEMMASCOPE-2-RES-65K
    7. 54767
    Prev
    Next
    INDEX
    Explanations

    producing intelligence; assessments

    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_65k_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
     تجاوز
    0.53
    諫
    0.46
    ร้าง
    0.46
     Ukraina
    0.46
    說是
    0.45
    竊
    0.45
     libertarian
    0.45
    ሳሪያ
    0.45
    娍
    0.44
     imigr
    0.44
    POSITIVE LOGITS
    ast
    0.51
    a
    0.47
    ome
    0.47
    emand
    0.47
    ového
    0.44
     가까
    0.43
    ↵↵
    0.42
    ;
    0.42
    ak
    0.41
    ich
    0.41
    Activations Density 0.006%

    No Known Activations