© 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. 173795
    Prev
    Next
    INDEX
    Explanations

    running the

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

    subprocess, each

    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
     Humanity
    0.50
     Discussions
    0.49
     Earlier
    0.48
     什么
    0.48
     Discussion
    0.47
     Thes
    0.47
     Conference
    0.47
    ু
    0.47
     Date
    0.46
     Hire
    0.46
    POSITIVE LOGITS
     metabol
    0.47
     metabolic
    0.45
    ianza
    0.44
    ියා
    0.42
     siphon
    0.41
     ਗਈ
    0.41
     inversion
    0.40
    linear
    0.40
     سع
    0.39
     kuj
    0.39
    Activations Density 0.000%

    No Known Activations