© 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. 2095
    Prev
    Next
    INDEX
    Explanations

    language

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

    making a difference

    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
    S
    0.57
     refresh
    0.55
     s
    0.54
     refres
    0.52
     plow
    0.50
     S
    0.49
    uj
    0.47
    s
    0.47
    refresh
    0.46
    mes
    0.46
    POSITIVE LOGITS
    잍
    0.49
     থাকতেন
    0.48
     działal
    0.48
     Translational
    0.47
    桷
    0.46
     نیاز
    0.46
    ၼ်
    0.45
     міні
    0.45
    apayati
    0.44
    ใหญ่
    0.44
    Activations Density 0.001%

    No Known Activations