© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12399
    Prev
    Next
    INDEX
    Explanations

    google followed by services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
    usermodel
    2.51
    ясплат
    2.48
    s
    2.38
    "',
    2.36
    ाग्राम
    2.31
    rest
    2.31
    黼
    2.19
    葆
    2.18
    𝗧
    2.17
    〢
    2.16
    POSITIVE LOGITS
    瘩
    2.21
    ން
    2.21
     “
    2.01
    름
    2.01
     답
    1.99
     rass
    1.98
    headed
    1.91
    UnitTest
    1.90
    AutoFocus
    1.89
     (“
    1.85
    Activations Density 0.092%

    No Known Activations