© 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. 53956
    Prev
    Next
    INDEX
    Explanations

    children playing outside

    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
    kelijk
    -0.79
     الرجل
    -0.77
    汀
    -0.76
     გ
    -0.74
    歩く
    -0.73
     المن
    -0.73
     homme
    -0.69
     przem
    -0.69
     бесе
    -0.69
     кур
    -0.69
    POSITIVE LOGITS
     play
    3.92
     playing
    3.30
    play
    3.03
     playtime
    2.70
     PLAY
    2.69
    Play
    2.63
    Playing
    2.58
     Play
    2.53
    PLAY
    2.53
    เล่น
    2.52
    Activations Density 0.061%

    No Known Activations