© 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. 1255
    Prev
    Next
    INDEX
    Explanations

    now followed by comma

    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
    Allocator
    2.80
    Near
    2.80
    unya
    2.63
    σιμοποι
    2.49
    দ্য
    2.45
    笂
    2.43
    ophyll
    2.43
    გან
    2.40
    戳
    2.39
    ग्ध
    2.39
    POSITIVE LOGITS
     endl
    3.36
     setw
    3.21
    ArrivalTime
    2.88
    letzt
    2.51
     ved
    2.50
    hatti
    2.44
     uj
    2.39
    메이션
    2.38
    Ved
    2.38
    कुंठ
    2.37
    Activations Density 0.062%

    No Known Activations