© 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. 210219
    Prev
    Next
    INDEX
    Explanations

    financial distress or replacement

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

    drive, early, ways, image, deeper

    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
     aerobic
    0.47
     I
    0.45
     Thames
    0.44
     sideways
    0.43
     EST
    0.42
     anaerobic
    0.42
     tweeted
    0.41
     aire
    0.40
    naio
    0.40
     serviced
    0.40
    POSITIVE LOGITS
     అల
    0.50
     נפ
    0.49
    郄
    0.49
    歟
    0.48
    委員會
    0.48
    遭到
    0.47
     감소
    0.46
    反对
    0.46
    贩
    0.45
    货币
    0.45
    Activations Density 0.001%

    No Known Activations