© 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. 2428
    Prev
    Next
    INDEX
    Explanations

    very well / less often

    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
     اس
    0.79
    chsel
    0.76
     ഹോ
    0.72
     바
    0.66
    滉
    0.64
    바
    0.64
    rę
    0.64
    ្វ
    0.64
     자신의
    0.63
    ग्विजय
    0.63
    POSITIVE LOGITS
     moins
    0.81
     десятки
    0.80
     sooner
    0.80
     кров
    0.80
    ing
    0.78
     tens
    0.76
     fewer
    0.76
     менее
    0.76
    Seconds
    0.75
     unsurprisingly
    0.74
    Activations Density 0.766%

    No Known Activations