© 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. 8730
    Prev
    Next
    INDEX
    Explanations

    relationships with others

    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
    วล
    1.31
    ญ
    1.27
    ᆭ
    1.27
     Sulfate
    1.23
     EFFECT
    1.22
     Rooney
    1.20
     Referenced
    1.20
     Effect
    1.19
     thin
    1.18
     Royce
    1.17
    POSITIVE LOGITS
     embark
    1.61
    δια
    1.51
     dabb
    1.45
    جهز
    1.44
     angem
    1.44
     reschedule
    1.44
    𝐦
    1.42
     embarking
    1.40
     δια
    1.39
    𝐣
    1.38
    Activations Density 0.000%

    No Known Activations