© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4530
    Prev
    Next
    INDEX
    Explanations

    sharing that

    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
    МІ
    1.49
    (\\
    1.46
    MORD
    1.41
     humbled
    1.40
    <unused1190>
    1.39
     interfere
    1.37
    𝐟
    1.34
    告訴
    1.34
    𝐰
    1.32
    攺
    1.30
    POSITIVE LOGITS
     By
    1.22
     Those
    1.09
     No
    1.08
     So
    1.04
     Ведь
    1.04
     Nacht
    1.01
     Almond
    1.00
     Meanwhile
    1.00
     licencia
    0.99
     दृश्य
    0.99
    Activations Density 0.023%

    No Known Activations