© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 179543
    Prev
    Next
    INDEX
    Explanations

    Ross Ice, lunch registrations, McNamara who, Mission Control

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

    current understanding of changes

    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
    اقی
    0.48
    ➩
    0.42
    稀
    0.41
    Maryland
    0.41
     belief
    0.40
     رحمت
    0.39
     culminating
    0.38
    ิ
    0.37
     quadratic
    0.37
     culminates
    0.37
    POSITIVE LOGITS
     kunde
    0.57
    kup
    0.57
     anz
    0.54
     konnten
    0.53
    kennung
    0.53
     leden
    0.53
     κατά
    0.52
     прове
    0.51
     konnte
    0.51
    ensor
    0.50
    Activations Density 0.000%

    No Known Activations