© 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-16K
    4. 9422
    Prev
    Next
    INDEX
    Explanations

    switch, switches, switching

    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
    ิศ
    2.32
    OpenGL
    2.26
     ड्रेस
    2.09
    餮
    2.08
    angin
    2.07
    Rooms
    2.07
    angka
    2.05
    SOI
    2.04
    üe
    2.04
    imek
    2.02
    POSITIVE LOGITS
    frog
    2.14
    റ
    2.05
    ்ச
    1.98
    scotch
    1.97
    ্ণ
    1.88
     মনির
    1.86
    跹
    1.84
    гыз
    1.82
     suced
    1.82
    )|$(
    1.81
    Activations Density 0.423%

    No Known Activations