© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9277
    Prev
    Next
    INDEX
    Explanations

    data cleaning and preprocessing

    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_13_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
    getNumberOf
    2.17
    %"
    2.12
    ره
    2.08
    ầng
    2.01
    ,"
    1.94
    \%$
    1.94
    $^{
    1.91
     nặng
    1.90
    riqu
    1.89
    蠣
    1.87
    POSITIVE LOGITS
    ীর
    2.66
    liness
    2.27
    ्सा
    2.10
     porttitor
    2.04
    ść
    2.01
    eworld
    2.00
    eced
    1.94
    ЭС
    1.91
    ্স
    1.90
    🧼
    1.89
    Activations Density 0.635%

    No Known Activations