© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 28890
    Prev
    Next
    INDEX
    Explanations

    comics and manga

    np_acts-logits-general · gemini-2.5-flash-lite

    comics and graphic novels

    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
    hotels
    0.50
     vorhand
    0.47
    NHS
    0.46
     kmeans
    0.45
    0.43
    esia
    0.42
    $$
    0.42
    荟
    0.42
    🐑
    0.41
     vorhanden
    0.41
    POSITIVE LOGITS
     comics
    1.45
     Comics
    1.37
     comic
    1.36
     Comic
    1.25
    comics
    1.23
    Comic
    1.18
    漫畫
    1.15
    漫画
    1.13
    comic
    1.06
     cartoonist
    0.89
    Activations Density 0.111%

    No Known Activations