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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 68589
    Prev
    Next
    INDEX
    Explanations

    suffering, game, rugby

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

    grammatical structures and specific terms

    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_31_width_262k_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
    反応
    0.41
    芸術
    0.41
    models
    0.39
    artists
    0.39
    scientists
    0.39
    aysia
    0.39
    尖
    0.38
    民眾
    0.38
    Nya
    0.38
    金属
    0.38
    POSITIVE LOGITS
     rugby
    0.49
     игра
    0.48
    级别的
    0.48
     очередной
    0.47
     game
    0.47
     нагрузки
    0.47
     ఆట
    0.47
     debería
    0.46
     tráfico
    0.46
    हमी
    0.46
    Activations Density 0.000%

    No Known Activations