© 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. 13-GEMMASCOPE-2-RES-65K
    7. 1529
    Prev
    Next
    INDEX
    Explanations

    people and their actions

    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
     RARRAY
    2.03
    𐰴
    1.81
    𒅆
    1.77
     Đá
    1.75
    𒉈
    1.75
     środow
    1.73
     BSData
    1.71
    ⇵
    1.71
    𒋫
    1.70
     ámbito
    1.69
    POSITIVE LOGITS
    ,
    1.40
     who
    1.36
    ’
    1.33
    '
    1.32
     of
    1.08
     spoke
    1.01
     himself
    1.01
     named
    0.96
    .
    0.95
     was
    0.93
    Activations Density 0.649%

    No Known Activations