© 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. 30475
    Prev
    Next
    INDEX
    Explanations

    :: code names

    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
    ли
    2.52
    त
    2.47
    ри
    2.41
    های
    2.23
    и
    2.23
    ે
    2.11
    у
    2.03
    น
    2.03
    iors
    1.95
    که
    1.88
    POSITIVE LOGITS
    ின்
    2.50
    sion
    2.17
    σιμοποι
    2.02
     provenienti
    1.91
    ിയ
    1.91
    ZIONE
    1.84
    RO
    1.82
    f
    1.80
    baz
    1.77
    か
    1.77
    Activations Density 0.013%

    No Known Activations