© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 224743
    Prev
    Next
    INDEX
    Explanations

    Be vivid

    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
     '**
    0.40
     ہی
    0.40
     captive
    0.39
    േരി
    0.38
    是多少
    0.37
    等人
    0.36
     computed
    0.36
    轿
    0.36
    られる
    0.35
    FieldValue
    0.35
    POSITIVE LOGITS
     exorc
    0.43
    Modelo
    0.43
    চা
    0.42
     agricoles
    0.39
     intercambio
    0.38
    কিন
    0.38
     कॉमर्स
    0.38
     لیست
    0.38
     તરી
    0.37
    ursos
    0.37
    Activations Density 0.002%

    No Known Activations