© 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. 14873
    Prev
    Next
    INDEX
    Explanations

    people who want to help

    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
    णिज्य
    1.55
    窕
    1.46
    CMAKE
    1.41
    hljs
    1.36
     contratto
    1.31
    кра
    1.28
     РАН
    1.27
    时的
    1.27
    ee
    1.27
    theless
    1.26
    POSITIVE LOGITS
    بە
    2.20
    د
    2.09
    ب
    2.06
    ו
    2.01
    т
    1.98
    н
    1.88
    ιδ
    1.87
    র
    1.84
     Trip
    1.82
    тни
    1.79
    Activations Density 0.069%

    No Known Activations