© 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. 87244
    Prev
    Next
    INDEX
    Explanations

    fasting and not eating

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

    Ramadan, body signals, code structures

    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
     Senin
    0.59
     Santorini
    0.54
     Nucl
    0.53
     HSV
    0.52
     Depth
    0.51
    䀨
    0.50
     Hercules
    0.49
     点
    0.49
     Bd
    0.49
     Assembl
    0.49
    POSITIVE LOGITS
    term
    0.47
    らが
    0.45
    vog
    0.43
    der
    0.43
     flaw
    0.43
    яви
    0.42
    Holds
    0.42
    Serv
    0.42
    ネル
    0.42
    Jährige
    0.42
    Activations Density 0.001%

    No Known Activations