© 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. 10213
    Prev
    Next
    INDEX
    Explanations

    fictional characters

    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
    udarstven
    0.51
    idefinite
    0.50
     sideWeight
    0.48
    ImageBeforeText
    0.48
    法院
    0.48
     superscript
    0.47
     organismes
    0.47
    緯
    0.47
    OLYBD
    0.47
     fdPar
    0.47
    POSITIVE LOGITS
     characters
    1.08
     Captain
    1.06
     Characters
    1.02
     Pikachu
    0.96
     Goku
    0.96
     Luffy
    0.95
    Captain
    0.92
    Characters
    0.91
     Anakin
    0.90
    characters
    0.89
    Activations Density 0.044%

    No Known Activations