© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 15966
    Prev
    Next
    INDEX
    Explanations

    melody: feel, ideas

    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_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
    ៉ុ
    1.82
     初始化
    1.81
    PERATURE
    1.80
    <unused325>
    1.79
    <unused716>
    1.77
    ጇ
    1.77
    <unused965>
    1.75
    <unused439>
    1.75
    ᚗ
    1.74
    Correlation
    1.74
    POSITIVE LOGITS
    um
    0.91
     part
    0.83
     von
    0.81
     parte
    0.77
    /
    0.77
     aktuell
    0.76
     Salim
    0.76
     pot
    0.75
    zelf
    0.71
     ag
    0.69
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.