© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 232693
    Prev
    Next
    INDEX
    Explanations

    vegan and free product claims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鸵
    0.49
    一定会
    0.48
    二百
    0.47
    timeouts
    0.46
    在我
    0.45
    一步
    0.45
     amis
    0.45
    熨
    0.44
    écut
    0.44
    AndWait
    0.44
    POSITIVE LOGITS
     Pó
    0.49
     songwriting
    0.46
     Tanganyika
    0.45
     producing
    0.45
     Si
    0.45
     cré
    0.45
     Kako
    0.44
     źród
    0.43
     ቀን
    0.43
     poetry
    0.43
    Activations Density 0.000%

    No Known Activations