© 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. 175138
    Prev
    Next
    INDEX
    Explanations

    Traffic safety and alerts

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

    code application

    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
     murm
    0.53
     assertThat
    0.51
     equival
    0.50
     mirrors
    0.47
     toler
    0.47
    راف
    0.47
    览
    0.45
    را
    0.44
     censoring
    0.44
     bets
    0.43
    POSITIVE LOGITS
    碜
    0.54
     тро
    0.51
     শ্যাম
    0.50
     שי
    0.50
     ลด
    0.50
     মণ
    0.49
    ISIONS
    0.48
     हेली
    0.48
     lắp
    0.47
     রো
    0.47
    Activations Density 0.000%

    No Known Activations