© 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. 193218
    Prev
    Next
    INDEX
    Explanations

    enjoyed the data

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

    mental health

    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
    达
    0.59
    时刻
    0.49
     pár
    0.46
    家伙
    0.45
    当天
    0.45
    库
    0.44
     geprü
    0.43
    给
    0.43
    一天
    0.42
     PCBs
    0.42
    POSITIVE LOGITS
    ey
    0.52
     fantasies
    0.50
     nodules
    0.50
     disorientation
    0.50
    oulder
    0.48
     urgency
    0.48
     baptism
    0.46
     scares
    0.46
     Baptism
    0.46
    antiation
    0.45
    Activations Density 0.000%

    No Known Activations