© 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. 120650
    Prev
    Next
    INDEX
    Explanations

    aliexpress or squash recipes

    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
     Instagram
    0.46
     Amazon
    0.45
     Polo
    0.44
    ຕ
    0.44
     TikTok
    0.43
    બ
    0.43
     Sushi
    0.42
    )^{\
    0.40
    Instagram
    0.40
    वली
    0.40
    POSITIVE LOGITS
    <unused72>
    0.44
    ंद
    0.44
    ایہ
    0.42
    ünschen
    0.40
     schützen
    0.39
    าน
    0.39
    óch
    0.38
    挸
    0.38
    Standard
    0.38
    orest
    0.38
    Activations Density 0.001%

    No Known Activations