© 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. 50565
    Prev
    Next
    INDEX
    Explanations

    "Well, hi"

    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
    ל
    0.50
    队列
    0.46
    ן
    0.45
     queue
    0.45
    าย
    0.42
    ก
    0.41
     vaccin
    0.41
    დი
    0.41
    ل
    0.41
    queue
    0.40
    POSITIVE LOGITS
    ≥</
    0.54
     কিংবা
    0.45
     Verification
    0.45
    どもの
    0.43
     ধারণা
    0.42
     अा
    0.41
     semidefinite
    0.41
     வரலா
    0.41
    粝
    0.41
     höch
    0.41
    Activations Density 0.000%

    No Known Activations