© 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. 697
    Prev
    Next
    INDEX
    Explanations

    amount of

    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
     the
    1.84
    ity
    1.83
    en
    1.83
    at
    1.72
    s
    1.67
    us
    1.65
    1.60
    ers
    1.56
    ness
    1.55
    ities
    1.54
    POSITIVE LOGITS
     setSnackbar
    3.62
    okatokat
    3.58
    𒀊
    3.56
    𒅅
    3.54
    𒉈
    3.52
    퍁
    3.46
     způ
    3.46
     különböző
    3.41
    AppBsky
    3.37
     samoglas
    3.35
    Activations Density 0.036%

    No Known Activations