© 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. 7-GEMMASCOPE-2-RES-16K
    7. 13042
    Prev
    Next
    INDEX
    Explanations

    primary vs secondary distinctions

    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_7_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
    stens
    2.65
    િ
    2.60
    
    2.57
    िक
    2.57
    酉
    2.57
    рку
    2.51
    Dise
    2.45
    遷
    2.41
    
    2.33
    ikte
    2.31
    POSITIVE LOGITS
     iyo
    2.18
    چی
    2.12
    hme
    2.09
    sley
    2.08
    шру
    2.03
    etrain
    2.02
    ्ड
    2.01
    الله
    2.00
    <bos>
    2.00
    ಸ್ಕ
    1.99
    Activations Density 0.028%

    No Known Activations