© 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. 24112
    Prev
    Next
    INDEX
    Explanations

    specialist Dr or non-English words

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

    departs at

    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
    。
    0.56
    演示
    0.49
    0.49
    .
    0.45
    ઈ
    0.43
    大
    0.43
     that
    0.42
     gases
    0.42
    ।
    0.42
     other
    0.41
    POSITIVE LOGITS
     anest
    0.45
     ⋅
    0.44
     Fleurit
    0.44
     कैंपस
    0.44
     রাজ্য
    0.43
     سری
    0.42
     ต้น
    0.42
     دانش
    0.42
     خراب
    0.42
    ⋅
    0.42
    Activations Density 0.000%

    No Known Activations