© 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. 13889
    Prev
    Next
    INDEX
    Explanations

    consulting an attorney

    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
    اً
    3.09
    nya
    3.03
    ا
    2.93
    اوى
    2.73
    اا
    2.72
    theless
    2.71
    dto
    2.65
    了
    2.50
    delay
    2.48
     lã
    2.47
    POSITIVE LOGITS
    ški
    2.45
     имају
    2.43
    planar
    2.41
     похађа
    2.40
     फ्लाई
    2.34
    тени
    2.29
    igal
    2.27
    łuż
    2.23
    。"
    2.22
     कोक
    2.22
    Activations Density 0.018%

    No Known Activations