© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1392
    Prev
    Next
    INDEX
    Explanations

    foreign characters, punctuation, code snippets

    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_17_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
    łac
    1.02
    ទំន
    0.89
    fli
    0.88
    =#
    0.87
    Figs
    0.86
    မူ
    0.86
    izare
    0.86
    arny
    0.85
    রাষ্ট্রম
    0.85
     पराम
    0.85
    POSITIVE LOGITS
     यानी
    1.35
     म्हणजेच
    1.25
     yani
    1.13
     यानि
    1.07
     (
    1.00
     नामक
    0.98
     (\"
    0.96
     એટલે
    0.96
     abbreviated
    0.94
     sorte
    0.94
    Activations Density 0.619%

    No Known Activations