© 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. 31-GEMMASCOPE-2-RES-16K
    4. 14233
    Prev
    Next
    INDEX
    Explanations

    policy, future, electoral

    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_16k_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
     haircuts
    0.47
     sugarcane
    0.40
    手游
    0.39
     Fireworks
    0.39
    uirre
    0.39
     Матери
    0.38
     estates
    0.38
    ՛
    0.37
     buttercream
    0.37
     เอ่อ
    0.36
    POSITIVE LOGITS
    CEA
    0.40
    лон
    0.39
    To
    0.39
    spirator
    0.38
    Ve
    0.38
    stoi
    0.37
    ült
    0.37
    ppa
    0.37
     নায়
    0.37
    Tol
    0.36
    Activations Density 0.000%

    No Known Activations