© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 983
    Prev
    Next
    INDEX
    Explanations

    an followed by a noun

    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
    <bos>
    3.55
    ৫
    2.88
    LESS
    2.81
    してい
    2.74
    ୍ୟ
    2.73
    しよう
    2.72
    payers
    2.69
    している
    2.67
    lettes
    2.63
    ں
    2.60
    POSITIVE LOGITS
    了
    4.36
    nya
    4.25
    self
    3.77
    ことができる
    3.68
    ことができます
    3.61
    sel
    3.54
    rd
    3.51
    다면
    3.45
    st
    3.43
    न
    3.43
    Activations Density 0.319%

    No Known Activations