© 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. 12-GEMMASCOPE-2-RES-16K
    7. 195
    Prev
    Next
    INDEX
    Explanations

    ball-shaped

    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_12_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
    ك
    0.72
    ת
    0.66
    ுறு
    0.65
    dni
    0.64
    sla
    0.63
     estreno
    0.63
    ﻞ
    0.62
    تي
    0.61
    دت
    0.61
    ف
    0.60
    POSITIVE LOGITS
     is
    0.72
     ofthe
    0.62
     of
    0.60
     was
    0.60
    あれば
    0.58
    。”
    0.58
     οποίο
    0.57
     are
    0.57
     in
    0.55
    о
    0.55
    Activations Density 0.484%

    No Known Activations