© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-262K
    7. 241723
    Prev
    Next
    INDEX
    Explanations

    variables and symbols

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_262k_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
    ++++++++
    0.52
     О
    0.52
     Inicio
    0.51
     ۾
    0.51
    פון
    0.49
    (((
    0.49
    radiated
    0.49
     ‫
    0.48
     fortale
    0.48
    ͕
    0.47
    POSITIVE LOGITS
     x
    1.23
    x
    0.91
     y
    0.82
    ｘ
    0.81
     u
    0.78
     k
    0.78
     xb
    0.77
     b
    0.76
     m
    0.75
     z
    0.75
    Activations Density 0.005%

    No Known Activations