© 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. 13780
    Prev
    Next
    INDEX
    Explanations

    legal terms, years, and fair use

    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
     बीच
    1.41
    r
    1.39
    rani
    1.38
    ibar
    1.37
    y
    1.36
    oq
    1.36
     klar
    1.34
    uen
    1.33
     balanced
    1.33
    شف
    1.33
    POSITIVE LOGITS
     वैलेंटाइन
    1.96
    ۱۰
    1.86
     մե
    1.85
    썬
    1.84
    optic
    1.82
     ELECTRON
    1.79
    १८
    1.77
    BEAN
    1.76
     Пу
    1.76
    ₃
    1.76
    Activations Density 0.044%

    No Known Activations