© 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. 1552
    Prev
    Next
    INDEX
    Explanations

    JSON structures and code

    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
    core
    2.80
    фона
    2.65
    𝚒
    2.65
    ionine
    2.63
    кса
    2.43
    ation
    2.42
    өрү
    2.38
    bir
    2.38
    enb
    2.35
    вобо
    2.33
    POSITIVE LOGITS
    s
    3.05
    tics
    2.82
    DEFGHIJKLMNOP
    2.80
    hung
    2.72
    sene
    2.66
    tble
    2.65
    으로
    2.58
    tive
    2.54
    sne
    2.47
     '+':
    2.46
    Activations Density 0.107%

    No Known Activations