© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13019
    Prev
    Next
    INDEX
    Explanations

    index pages

    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
    wrapperEl
    2.12
    gdock
    1.93
    subsetneq
    1.85
    氅
    1.85
    kotlin
    1.85
     sparsim
    1.84
    陘
    1.82
    <unused907>
    1.80
    ဠ
    1.78
    രള
    1.78
    POSITIVE LOGITS
    Your
    2.56
     yourself
    2.49
     your
    2.35
     Your
    2.32
     YOUR
    2.05
    YOUR
    1.92
    your
    1.90
     Yourself
    1.85
     будете
    1.84
    你自己
    1.78
    Activations Density 1.155%

    No Known Activations