© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11692
    Prev
    Next
    INDEX
    Explanations

    season opener, finale, ticket

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

    season and seasonal contexts

    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_40_width_16k_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
     scroll
    0.43
     rend
    0.43
     dispersion
    0.39
     period
    0.39
    ter
    0.39
    unen
    0.39
    𝜎
    0.39
    贞
    0.38
    Bo
    0.38
     sme
    0.38
    POSITIVE LOGITS
     finale
    0.67
     Finale
    0.67
    SEASON
    0.67
     opener
    0.66
     SEASON
    0.66
    Finale
    0.64
    finale
    0.63
    Season
    0.61
    season
    0.60
     시즌
    0.59
    Activations Density 0.047%

    No Known Activations