© 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. 144931
    Prev
    Next
    INDEX
    Explanations

    instructions and usage

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

    depending on

    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
    AppBsky
    0.55
    然後
    0.49
     फाइनेंस
    0.48
    🏫
    0.47
     Χ
    0.46
     설립
    0.45
    rypted
    0.45
     Bukan
    0.45
     Ř
    0.44
     περίπτωση
    0.44
    POSITIVE LOGITS
     urine
    0.51
     prayer
    0.49
    0
    0.48
    prayer
    0.46
     water
    0.44
    ার
    0.44
     she
    0.44
     awake
    0.43
     tube
    0.43
     voltam
    0.43
    Activations Density 0.002%

    No Known Activations