© 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. 43163
    Prev
    Next
    INDEX
    Explanations

    anime, games, and archetypes

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

    superhero and game character power comparisons

    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
     https
    0.50
     grandchild
    0.48
    🥹
    0.44
     sailboat
    0.43
    専門店
    0.43
     contactless
    0.43
    民宿
    0.43
    🤍
    0.43
    🥸
    0.43
    🧭
    0.42
    POSITIVE LOGITS
    Anime
    0.64
    Minecraft
    0.60
     Pikachu
    0.59
     Skyrim
    0.58
    Pokemon
    0.54
     anime
    0.53
     Overwatch
    0.53
     pacif
    0.52
    Pokémon
    0.52
    Gamepad
    0.52
    Activations Density 0.035%

    No Known Activations