© 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. 53-GEMMASCOPE-2-RES-65K
    7. 3256
    Prev
    Next
    INDEX
    Explanations

    Zhao Feng

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

    yes response

    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_53_width_65k_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
     мы
    0.46
     ఎక్కువగా
    0.46
     corrective
    0.43
    BigAutoField
    0.43
     externalities
    0.43
    脷
    0.43
    ⬥
    0.43
     bize
    0.42
     مداخل
    0.42
     variations
    0.42
    POSITIVE LOGITS
    唰
    0.96
    Seeing
    0.86
    咚
    0.86
     Seeing
    0.85
    boom
    0.83
    嘭
    0.81
     Hearing
    0.81
    嗡
    0.80
    噗
    0.79
    哐
    0.78
    Activations Density 0.013%

    No Known Activations