© 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. 13-GEMMASCOPE-2-RES-65K
    7. 2148
    Prev
    Next
    INDEX
    Explanations

    composite indexes, national unity, alloys

    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_13_width_65k_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
     laissé
    1.46
    ların
    1.44
    螓
    1.39
     güzel
    1.35
     বাঙ্গালার
    1.35
    yrıca
    1.35
     latitudine
    1.34
     uzun
    1.34
     pie
    1.34
    aların
    1.32
    POSITIVE LOGITS
    uari
    0.91
    u
    0.89
    <b>
    0.88
    a
    0.84
     معنات
    0.82
    었는데
    0.81
    coded
    0.81
     =
    0.81
    ா
    0.80
     then
    0.80
    Activations Density 0.000%

    No Known Activations