© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1787
    Prev
    Next
    INDEX
    Explanations

    decimal points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    Attribute
    0.70
    经
    0.65
    getAttribute
    0.63
    crets
    0.63
     घायल
    0.62
    clientX
    0.62
    ΕΣ
    0.62
    𝚆
    0.61
    ल्हा
    0.61
    œuf
    0.60
    POSITIVE LOGITS
    dot
    1.16
     dot
    1.04
     Dot
    1.01
    Dot
    0.99
     দশমিক
    0.94
    DOT
    0.93
    ᱹ
    0.90
     DOT
    0.89
     दशमलव
    0.86
     coma
    0.77
    Activations Density 0.320%

    No Known Activations