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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4719
    Prev
    Next
    INDEX
    Explanations

    breaking down concepts

    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
    怀孕
    1.28
     หนู
    1.25
     введен
    1.25
    決勝
    1.23
     آپریشن
    1.22
    这一次
    1.21
     núcle
    1.20
     那
    1.20
     svojih
    1.17
     前回
    1.16
    POSITIVE LOGITS
     trait
    1.02
     simple
    0.94
     unique
    0.91
    0.89
    !
    0.88
     can
    0.83
     individual
    0.82
     may
    0.80
     true
    0.79
    simple
    0.78
    Activations Density 0.213%

    No Known Activations