© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11120
    Prev
    Next
    INDEX
    Explanations

    sleep, relaxation, and physical comfort

    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
    従
    1.02
     құ
    0.97
    rium
    0.92
    èles
    0.90
    aneity
    0.89
    grades
    0.88
    arikat
    0.87
    ellite
    0.87
    冕
    0.86
     পর্যাপ্ত
    0.85
    POSITIVE LOGITS
     Lives
    1.47
     lives
    1.45
     notebook
    1.32
    Lives
    1.26
     indelible
    1.22
     rewriting
    1.21
     deja
    1.20
     rewrite
    1.20
     profoundly
    1.19
    Cursors
    1.19
    Activations Density 0.213%

    No Known Activations