© 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. 13815
    Prev
    Next
    INDEX
    Explanations

    Grandfather Paradox or Jet Stream

    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
    ়া
    2.41
    ยว
    2.37
    ogener
    2.22
    鴦
    2.22
    𝖊
    2.19
    ocrat
    2.16
    ocracy
    2.16
    ഹമ്മ
    2.13
    蜍
    2.12
    स्तान
    2.11
    POSITIVE LOGITS
    a
    4.64
    er
    4.43
    y
    4.22
    ה
    4.17
    en
    4.04
    an
    3.96
    る
    3.95
    e
    3.91
    ン
    3.88
    ে
    3.66
    Activations Density 0.004%

    No Known Activations