© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13657
    Prev
    Next
    INDEX
    Explanations

    seriously?!

    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_7_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
    溂
    3.28
    urring
    3.23
    Ｈ
    3.08
     oligonucle
    3.05
     />';
    3.04
    嚮
    2.86
    ávání
    2.80
    णिज्य
    2.77
     nucleons
    2.76
    क्टर
    2.71
    POSITIVE LOGITS
    нской
    2.74
    깐
    2.66
    н
    2.61
    אות
    2.51
    c
    2.50
    nst
    2.27
     grades
    2.27
    in
    2.26
    тельному
    2.24
    a
    2.24
    Activations Density 0.008%

    No Known Activations