© 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. 4582
    Prev
    Next
    INDEX
    Explanations

    are likely, there, run

    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
    0.72
     ‘
    0.69
    প
    0.68
     “
    0.68
    ด
    0.67
    بل
    0.65
    和一个
    0.64
    ก
    0.64
     AND
    0.62
    และความ
    0.62
    POSITIVE LOGITS
    ą
    0.83
    an
    0.75
    ím
    0.74
    speople
    0.72
    gave
    0.68
     tę
    0.67
     whereof
    0.66
     sứ
    0.65
    т
    0.65
     строку
    0.64
    Activations Density 0.266%

    No Known Activations