© 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. 166048
    Prev
    Next
    INDEX
    Explanations

    FROM meals, Having said, is gone

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

    plant, scapes, directory

    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
    ।"
    0.45
    শ
    0.39
     irrigation
    0.39
     রবি
    0.39
    让我
    0.39
     rerun
    0.38
    ⅜
    0.38
    铝
    0.38
     Weld
    0.38
     Welding
    0.38
    POSITIVE LOGITS
     प्रजा
    0.44
    AVE
    0.43
    ARA
    0.43
    وندی
    0.43
     পূর্বে
    0.42
     prób
    0.42
    ICON
    0.41
     Andere
    0.41
     стару
    0.41
    ECTOR
    0.41
    Activations Density 0.000%

    No Known Activations