© 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. 159778
    Prev
    Next
    INDEX
    Explanations

    King of Meteor Showers

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

    needed everything before

    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
    u
    0.49
    cropping
    0.48
    i
    0.45
    tis
    0.44
    department
    0.43
    iid
    0.43
    event
    0.43
    departments
    0.41
    physiology
    0.41
    dwelling
    0.41
    POSITIVE LOGITS
     ર
    0.50
     części
    0.48
     શબ્
    0.46
     pail
    0.45
     grandes
    0.45
     surged
    0.45
     progr
    0.44
     poveć
    0.44
     പഴയ
    0.44
     favorites
    0.43
    Activations Density 0.002%

    No Known Activations