© 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. 13550
    Prev
    Next
    INDEX
    Explanations

    lists and explanations with colons

    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
    ;',
    1.33
    essoas
    1.31
    рово
    1.29
    それは
    1.27
     называется
    1.22
    otan
    1.20
     '.',
    1.18
    ,'
    1.17
    बता
    1.17
    ',
    1.17
    POSITIVE LOGITS
     Auss
    1.10
    மார
    1.09
    ˚
    1.03
     fl
    1.02
     bedding
    1.02
     marg
    1.01
     prag
    1.00
     banner
    1.00
    ages
    1.00
    flu
    0.98
    Activations Density 0.000%

    No Known Activations