© 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. 167358
    Prev
    Next
    INDEX
    Explanations

    pronoun subjects performing actions

    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
    㚼
    0.45
     Permits
    0.44
    เช่น
    0.42
     (“
    0.41
    漢
    0.41
     இப்படி
    0.39
     Permissions
    0.39
    ⇣
    0.39
     כמו
    0.38
     👇
    0.38
    POSITIVE LOGITS
     fell
    0.56
     spoke
    0.55
     wurde
    0.54
     died
    0.52
     awoke
    0.51
     gave
    0.50
     went
    0.49
     took
    0.49
     drew
    0.47
     congratulated
    0.46
    Activations Density 0.033%

    No Known Activations