© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 14090
    Prev
    Next
    INDEX
    Explanations

    pokemon

    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/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     syphilit
    0.48
    かもし
    0.44
    🧔
    0.44
    船舶
    0.44
    瀋
    0.43
     Jesuits
    0.43
     samoglas
    0.42
    徙
    0.42
     intravascular
    0.41
     Tolstoy
    0.41
    POSITIVE LOGITS
     Pokemon
    2.05
     pokemon
    2.02
     Pokémon
    1.99
    Pokemon
    1.90
    Pokémon
    1.81
    pokemon
    1.63
    ポケモン
    1.63
     Poké
    1.49
     Pikachu
    1.39
    Pok
    1.38
    Activations Density 0.025%

    No Known Activations