© 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. 155498
    Prev
    Next
    INDEX
    Explanations

    found around the

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

    peace and happiness

    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
    請問
    0.52
    網絡
    0.48
     tributaries
    0.46
    圖
    0.46
     ミ
    0.46
     turnovers
    0.45
    atmosphere
    0.44
    unks
    0.44
    ateľ
    0.44
     transitions
    0.43
    POSITIVE LOGITS
    (
    0.54
    리는
    0.48
     vencedor
    0.48
     Gewinn
    0.47
    (<
    0.47
     Sequelize
    0.44
     нә
    0.44
     теннис
    0.44
     Lippincott
    0.44
     Liefer
    0.43
    Activations Density 0.001%

    No Known Activations