© 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. 99
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and field names

    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
     centralized
    1.27
    <unused46>
    1.27
    <unused1197>
    1.20
     보다
    1.20
    <unused986>
    1.18
    <unused2165>
    1.18
    <unused913>
    1.18
    <unused1256>
    1.17
    dcsset
    1.16
    <unused350>
    1.16
    POSITIVE LOGITS
     valamint
    0.89
     немец
    0.88
     và
    0.86
     német
    0.83
     zwier
    0.78
     japonesa
    0.78
    ↵
    0.77
    burn
    0.76
     cherche
    0.75
     पहुंच
    0.75
    Activations Density 0.564%

    No Known Activations