© 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. 13750
    Prev
    Next
    INDEX
    Explanations

    upon followed by action or event

    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
    lerinde
    3.25
    leri
    3.02
    siniz
    2.83
    nen
    2.80
    서
    2.80
    lere
    2.79
    leriyle
    2.76
    lerinin
    2.75
    ler
    2.73
    lerde
    2.72
    POSITIVE LOGITS
    ו
    5.18
    ي
    4.55
    an
    4.12
    o
    3.93
    u
    3.69
    ার
    3.43
    a
    3.37
    る
    3.35
    en
    3.14
    objet
    3.03
    Activations Density 0.018%

    No Known Activations