© 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. 190525
    Prev
    Next
    INDEX
    Explanations

    services and information

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

    explaining science and concepts

    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
     exclaimed
    0.52
     enjeux
    0.49
     phosphoryl
    0.47
    rk
    0.45
     디지털
    0.45
     Tablets
    0.43
    ⓗ
    0.43
     дочери
    0.43
     inked
    0.42
     ऐप्स
    0.42
    POSITIVE LOGITS
    的做法
    0.51
    莧
    0.50
    टिया
    0.50
    arran
    0.45
    Caucasian
    0.44
    Capital
    0.43
    নেল
    0.43
    PolicyQuery
    0.43
    Missouri
    0.42
    格兰
    0.42
    Activations Density 0.000%

    No Known Activations