© 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. 13500
    Prev
    Next
    INDEX
    Explanations

    word followed by situation

    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
     izvr
    1.69
    ا
    1.62
     сразу
    1.58
     трёх
    1.58
    ви
    1.54
    erus
    1.54
    ಿ
    1.53
     maquin
    1.52
    ง
    1.52
     нескольких
    1.51
    POSITIVE LOGITS
    haired
    1.52
     cultivators
    1.47
    ler
    1.37
    rahydro
    1.36
    rt
    1.36
    éd
    1.32
    pytorch
    1.32
    lights
    1.31
    lere
    1.30
     Scrolls
    1.28
    Activations Density 0.000%

    No Known Activations