© 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. 23677
    Prev
    Next
    INDEX
    Explanations

    anime and manga character names

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

    anime manga sales and character arcs

    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
     ग्ले
    0.61
    槳
    0.61
    ल्ट
    0.60
    ندر
    0.60
    鉚
    0.58
    ştir
    0.58
    कार्बन
    0.57
    綠
    0.57
    輥
    0.55
    लिनी
    0.55
    POSITIVE LOGITS
     anime
    1.31
     manga
    1.30
     Anime
    1.25
    Anime
    1.18
     chibi
    1.10
     Luffy
    1.07
     Sakura
    1.05
     일본
    1.04
     Naruto
    1.04
     sakura
    1.02
    Activations Density 0.080%

    No Known Activations