© 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. 111599
    Prev
    Next
    INDEX
    Explanations

    ordinary, commonplace, everyday

    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
    ença
    0.44
    is
    0.39
    entery
    0.38
     بتر
    0.37
    /(:
    0.36
    alate
    0.36
    वाय
    0.35
    inales
    0.35
    height
    0.35
    ️
    0.34
    POSITIVE LOGITS
     SqlConnection
    0.45
     HttpSession
    0.43
     pengguna
    0.43
    SQL
    0.41
     callable
    0.41
     affordable
    0.40
     sessionId
    0.40
     session
    0.40
     bitmaps
    0.40
     dermatologist
    0.40
    Activations Density 0.001%

    No Known Activations