© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 365
    Prev
    Next
    INDEX
    Explanations

    it becomes or quickly

    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
    o
    1.94
    hand
    1.86
     ovo
    1.79
    B
    1.78
    ianza
    1.76
    قیم
    1.75
     auxquels
    1.70
     B
    1.66
    +
    1.64
    ที่มี
    1.63
    POSITIVE LOGITS
    <unused2223>
    2.74
    inerary
    2.72
    <unused2222>
    2.65
    <unused1157>
    2.56
     happened
    2.53
     seems
    2.48
     happens
    2.48
    <unused1130>
    2.46
     dawned
    2.41
    elligence
    2.39
    Activations Density 0.684%

    No Known Activations