© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99648
    Prev
    Next
    INDEX
    Explanations

    anime and adaptations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Manga
    -0.85
     Heft
    -0.76
     Pitts
    -0.75
     Anime
    -0.74
    manga
    -0.73
    Anime
    -0.73
    Enlla
    -0.73
    Ể
    -0.73
     seasonal
    -0.72
     yyb
    -0.72
    POSITIVE LOGITS
     irgendwann
    0.84
     Outbreak
    0.78
    OVER
    0.78
    Install
    0.77
     engraved
    0.75
    Protocol
    0.75
    发生
    0.75
    >//
    0.74
     infestation
    0.74
     golfers
    0.73
    Activations Density 0.035%

    No Known Activations