© 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-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 8412
    Prev
    Next
    INDEX
    Explanations

    'that' followed by specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    o
    0.80
    c
    0.76
    ول
    0.73
    ী
    0.71
    I
    0.68
    ة
    0.67
    r
    0.64
    ो
    0.64
    كة
    0.64
     I
    0.64
    POSITIVE LOGITS
    一方で
    0.93
    然而
    0.83
    不仅
    0.81
    nimi
    0.80
    在这种
    0.79
    τές
    0.79
    že
    0.77
    并将
    0.77
    并在
    0.77
    并不是
    0.76
    Activations Density 0.346%

    No Known Activations