© 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. 13-GEMMASCOPE-2-RES-65K
    4. 834
    Prev
    Next
    INDEX
    Explanations

    for X (purpose/condition)

    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_65k_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
    et
    1.27
    es
    1.23
    는
    1.17
    ised
    1.17
    은
    1.17
    は
    1.12
    of
    1.10
    erson
    1.09
    ette
    1.08
    are
    1.06
    POSITIVE LOGITS
    geries
    1.52
     unfore
    1.38
     starters
    1.29
     prejudicial
    1.27
    BlogPost
    1.23
     thisComponent
    1.22
     sajana
    1.22
     betterment
    1.21
     sConfig
    1.21
    <unused1911>
    1.21
    Activations Density 0.929%

    No Known Activations