© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7960
    Prev
    Next
    INDEX
    Explanations

    how things work or are done

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
    zmdi
    0.62
     prosegu
    0.58
    𝗗
    0.56
     avendo
    0.55
     brevi
    0.54
     sini
    0.54
     እየ
    0.54
    으로부터
    0.54
     melanogaster
    0.54
     Dairy
    0.53
    POSITIVE LOGITS
    வர்
    0.55
     ут
    0.54
    Cfg
    0.53
     shortcuts
    0.52
    UTO
    0.52
     an
    0.52
    k
    0.52
     মেয়র
    0.51
    y
    0.50
     관련
    0.50
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.