© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 26655
    Prev
    Next
    INDEX
    Explanations

    negative prompts: cartoon, anime, illustration

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    kadang
    0.41
    command
    0.41
    etail
    0.40
    沏
    0.39
    ждую
    0.39
     varied
    0.38
    ，「
    0.38
    ⼈
    0.38
     intricate
    0.38
     करावे
    0.38
    POSITIVE LOGITS
     cartoons
    0.61
     animaux
    0.59
     cartoon
    0.58
     Cartoon
    0.55
    cartoon
    0.54
    Cartoon
    0.51
     animales
    0.48
     animali
    0.46
     childish
    0.46
     vampires
    0.46
    Activations Density 0.002%

    No Known Activations