© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65495
    Prev
    Next
    INDEX
    Explanations

    seasonal events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    बार
    -0.75
    ITERIA
    -0.71
     professionally
    -0.69
    τας
    -0.69
    änk
    -0.68
    了我
    -0.68
    ური
    -0.68
    correspond
    -0.68
    akov
    -0.68
    ornos
    -0.68
    POSITIVE LOGITS
     season
    7.09
    season
    4.88
     Season
    4.78
    Season
    4.50
     seasons
    4.41
     SEASON
    3.81
     temporada
    3.53
    SEASON
    3.28
     stagione
    3.23
    シーズン
    3.19
    Activations Density 0.067%

    No Known Activations