© 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. 13960
    Prev
    Next
    INDEX
    Explanations

    boxed answers

    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
    喿
    2.72
    <unused1951>
    2.64
    <0x1E>
    2.63
    阠
    2.61
    <unused1701>
    2.60
    甶
    2.60
    <unused730>
    2.58
    夰
    2.57
    ₚ
    2.54
     Фон
    2.53
    POSITIVE LOGITS
    uckles
    2.06
    D
    1.87
    sets
    1.81
    set
    1.62
    C
    1.57
     null
    1.41
    null
    1.41
     som
    1.39
    min
    1.37
    ,,,,
    1.36
    Activations Density 0.019%

    No Known Activations