© 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-16K
    7. 1244
    Prev
    Next
    INDEX
    Explanations

    internet addresses

    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
    viewer
    1.69
    umpang
    1.50
    weight
    1.40
    ဆ
    1.36
     reconsider
    1.35
    robe
    1.32
     paralys
    1.29
    watching
    1.28
     Baru
    1.27
    вос
    1.27
    POSITIVE LOGITS
    StringTo
    1.43
    产权
    1.39
     常
    1.34
    ッキング
    1.32
     classiques
    1.29
    ቂያ
    1.29
     정확
    1.26
     cleft
    1.25
    ার্টমেন্ট
    1.24
     υπάρχ
    1.24
    Activations Density 0.575%

    No Known Activations