© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48030
    Prev
    Next
    INDEX
    Explanations

    listing or tracking difficulty

    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_31_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
    0.52
    u
    0.49
    輸入
    0.46
    /
    0.46
    نا
    0.46
    이다
    0.45
    obytes
    0.43
    生
    0.42
    
    0.42
    清
    0.42
    POSITIVE LOGITS
     güncelle
    0.52
     exclusivity
    0.51
     involunt
    0.50
     jobId
    0.48
     ईमित्र
    0.48
    ્લે
    0.48
    ロナ
    0.48
    ᴵ
    0.47
     monetization
    0.47
     trophies
    0.47
    Activations Density 0.003%

    No Known Activations