© 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. 2414
    Prev
    Next
    INDEX
    Explanations

    MATLAB

    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
     みたい
    1.35
     اخ
    1.35
    ടക
    1.28
    Соцмережа
    1.27
    <unused617>
    1.27
    <unused1039>
    1.27
    <unused215>
    1.26
    <unused235>
    1.25
     関数
    1.25
     に
    1.24
    POSITIVE LOGITS
    gles
    0.90
    herlands
    0.82
    amas
    0.78
    ismer
    0.77
    plica
    0.76
    zont
    0.75
     pro
    0.74
    aber
    0.74
    hausen
    0.74
    ้อง
    0.74
    Activations Density 0.071%

    No Known Activations