© 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. 88659
    Prev
    Next
    INDEX
    Explanations

    sentence end marker"

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

    operators and technical terms

    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
     små
    0.49
     chocolate
    0.47
    1
    0.47
     of
    0.46
    奥运
    0.46
    ø
    0.46
    映
    0.45
    小
    0.45
    ør
    0.44
     improvis
    0.44
    POSITIVE LOGITS
     ہوگا
    0.54
    خواهد
    0.50
     سيكون
    0.48
     هيكون
    0.47
     خواهد
    0.46
    ഽ
    0.46
     വിഭാഗ
    0.43
    ائف
    0.42
     ہوگا۔
    0.42
     வழங்கப்படும்
    0.42
    Activations Density 0.001%

    No Known Activations