© 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. 24-GEMMASCOPE-2-RES-16K
    7. 8774
    Prev
    Next
    INDEX
    Explanations

    UI setup and graphical contexts

    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_24_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
    々の
    0.50
    ^{*}
    0.47
     eigene
    0.46
    3
    0.46
     seterusnya
    0.46
     newest
    0.46
    4
    0.46
     photograph
    0.45
    Photograph
    0.44
    _
    0.44
    POSITIVE LOGITS
     başladı
    0.59
     inicialmente
    0.58
     judul
    0.58
    inicio
    0.57
     पदक
    0.57
     શરૂ
    0.57
     başlang
    0.56
    났
    0.55
    titulo
    0.52
     pasos
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.