© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 205792
    Prev
    Next
    INDEX
    Explanations

    food establishment or older generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yearling
    0.40
     anaemia
    0.39
     ass
    0.38
    হরণ
    0.38
    聯
    0.37
     neuritis
    0.36
    விட்டு
    0.36
     নির
    0.35
     বলিয়া
    0.35
    社會
    0.35
    POSITIVE LOGITS
     призна
    0.44
     günü
    0.43
    romeda
    0.42
    ánicos
    0.39
    쿱
    0.39
    ন্দে
    0.39
    لمانيا
    0.38
     gün
    0.38
    饪
    0.38
     recognized
    0.38
    Activations Density 0.000%

    No Known Activations