© 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. 13768
    Prev
    Next
    INDEX
    Explanations

    43

    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
    omitempty
    1.58
     sekolah
    1.53
    尤其是
    1.52
     특히
    1.52
     transporting
    1.51
    𒂵
    1.51
     takže
    1.50
     включая
    1.49
    특히
    1.48
    ்சைடு
    1.47
    POSITIVE LOGITS
    ,
    1.65
    :
    1.54
    /
    1.50
    (
    1.43
    ’
    1.43
    '
    1.43
    (?)
    1.37
    ...
    1.34
    ،
    1.33
    .
    1.31
    Activations Density 0.034%

    No Known Activations