© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 94452
    Prev
    Next
    INDEX
    Explanations

    activity

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

    following up

    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
    Negative Logits
    спект
    0.50
    ИС
    0.48
    ками
    0.44
    ToTensor
    0.43
    ಪಟ್ಟ
    0.42
    特
    0.42
    山本
    0.42
    ול
    0.40
    скоп
    0.40
    ﺭ
    0.40
    POSITIVE LOGITS
     اجتماع
    0.55
     Modifications
    0.52
     monitor
    0.48
     Monitoring
    0.48
     Modify
    0.46
     modify
    0.46
     连接
    0.46
    modify
    0.45
    upp
    0.45
    想想
    0.45
    Activations Density 0.000%

    No Known Activations