© 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. 9105
    Prev
    Next
    INDEX
    Explanations

    controller classes

    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
    werten
    2.12
    𝒚
    1.98
    𝒎
    1.83
     linewidth
    1.83
    ায়ী
    1.81
    ваме
    1.76
    πων
    1.71
    긋
    1.70
    mour
    1.68
    y
    1.68
    POSITIVE LOGITS
     المل
    2.01
     ألف
    1.94
     والذي
    1.93
     Eg
    1.91
     شنو
    1.89
     Aks
    1.89
     Parad
    1.88
    ெ
    1.88
     Samar
    1.88
     Cop
    1.87
    Activations Density 0.006%

    No Known Activations