© 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. 4103
    Prev
    Next
    INDEX
    Explanations

    putting on pajamas

    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
    𝚜
    1.58
    adeon
    1.54
     computes
    1.49
     maturities
    1.49
    <unused404>
    1.48
     海外
    1.47
     लकार
    1.47
     geometrical
    1.47
     Deformation
    1.45
    々の
    1.44
    POSITIVE LOGITS
    s
    1.27
    нди
    1.11
    ample
    1.08
     нашли
    1.01
     nú
    0.99
    mgr
    0.98
    harvard
    0.94
     «
    0.94
     desco
    0.93
    :
    0.93
    Activations Density 0.000%

    No Known Activations