© 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. 8315
    Prev
    Next
    INDEX
    Explanations

    applied to specific contexts

    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
    槤
    1.72
    𝔻
    1.70
    笳
    1.62
     inept
    1.62
    是很
    1.59
     exag
    1.54
     REALLY
    1.54
     CTL
    1.54
     TES
    1.54
     anderes
    1.52
    POSITIVE LOGITS
    vena
    1.38
    Upper
    1.36
    Deep
    1.35
    ઇ
    1.31
    Splash
    1.30
    ez
    1.27
    Stock
    1.26
    find
    1.24
    enjoy
    1.22
    Retrieve
    1.18
    Activations Density 0.000%

    No Known Activations