© 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-16K
    4. 129
    Prev
    Next
    INDEX
    Explanations

    AI self-description of abilities

    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
     Ven
    1.77
     Fel
    1.77
     Jean
    1.70
     Hel
    1.66
     Mol
    1.66
     Kaplan
    1.64
     µ
    1.64
     Heide
    1.62
     Euro
    1.62
     Ho
    1.62
    POSITIVE LOGITS
     لوبوي
    1.32
    の状態
    1.25
     божомолу
    1.23
    spapers
    1.21
    চ্
    1.16
    来进行
    1.14
    数据显示
    1.14
    屋さん
    1.14
    瞅
    1.12
    ⁉
    1.12
    Activations Density 0.445%

    No Known Activations