© 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. 13242
    Prev
    Next
    INDEX
    Explanations

    amounts, prices, and salaries

    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
    initComponents
    2.36
    ________________
    2.32
    pain
    2.27
    댓
    2.19
    בוע
    2.17
    λλη
    2.12
    ment
    2.05
    결
    1.97
    l
    1.97
    }.${
    1.95
    POSITIVE LOGITS
    Collider
    2.88
    іл
    2.82
    ignés
    2.71
    эння
    2.58
    ўся
    2.56
    COLOR
    2.50
    вся
    2.50
    ioon
    2.49
     perspiciatis
    2.49
    闱
    2.46
    Activations Density 0.008%

    No Known Activations