© 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. 840
    Prev
    Next
    INDEX
    Explanations

    local http endpoints

    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
    ാ
    2.75
    iate
    2.67
    ы
    2.67
    ки
    2.60
    ing
    2.58
    ের
    2.42
    ت
    2.26
    evice
    2.23
    houd
    2.21
    |^{
    2.21
    POSITIVE LOGITS
    া
    2.54
    彡
    2.47
    皰
    2.45
    ｍ
    2.40
    裟
    2.38
    स्यों
    2.37
    あえず
    2.34
     Anf
    2.32
    ichlet
    2.31
    াত্য
    2.22
    Activations Density 0.220%

    No Known Activations