© 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. 954
    Prev
    Next
    INDEX
    Explanations

    data assignment and modification

    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
     maternelle
    0.81
    料金
    0.81
    
    0.80
     Aussage
    0.79
    ഊ
    0.78
    아이
    0.75
    нём
    0.75
    アメリカ
    0.74
    みんな
    0.73
    日本語
    0.73
    POSITIVE LOGITS
    ihilation
    0.70
    +"|
    0.68
    warz
    0.65
    zug
    0.62
    undle
    0.61
    auschen
    0.61
    quisite
    0.59
    abling
    0.58
    ectors
    0.57
    ḗ
    0.57
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.