© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 101735
    Prev
    Next
    INDEX
    Explanations

    Thomas Rhett and Carrie Underwood

    np_acts-logits-general · gemini-2.5-flash-lite

    José Arcadio Buendía, Shakira, songs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鹘
    0.46
    乗り
    0.45
    声音
    0.42
    Stay
    0.42
     आवाज
    0.41
    喍
    0.40
    乘坐
    0.40
    吘
    0.39
    駒
    0.39
    跇
    0.38
    POSITIVE LOGITS
     Dublin
    0.47
     chaos
    0.43
     teritor
    0.41
     xo
    0.41
     intensidad
    0.40
     Iglesia
    0.39
     Mediterranean
    0.39
     incapac
    0.39
     Lain
    0.39
     Osc
    0.38
    Activations Density 0.006%

    No Known Activations