© 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. 184643
    Prev
    Next
    INDEX
    Explanations

    locations and concepts

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

    implies or appears

    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
    中心
    0.50
     Centre
    0.47
     Platform
    0.46
    现有
    0.45
     Kotlin
    0.45
    ，
    0.45
     platform
    0.45
     System
    0.44
     lồ
    0.44
     Start
    0.44
    POSITIVE LOGITS
     グッチ
    0.51
     ತುಂಬಾ
    0.51
    abha
    0.50
     काफ़ी
    0.50
    тун
    0.48
     काफी
    0.47
    residents
    0.47
     ಸುಮ
    0.46
    භ
    0.46
    instell
    0.46
    Activations Density 0.000%

    No Known Activations