© 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. 24-GEMMASCOPE-2-RES-16K
    7. 5073
    Prev
    Next
    INDEX
    Explanations

    sections

    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_24_width_16k_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
     செ
    0.84
    PTS
    0.83
    ogany
    0.81
     lassen
    0.80
    将会
    0.79
    只会
    0.75
    L
    0.74
    されていない
    0.73
    र्गत
    0.72
    அ
    0.72
    POSITIVE LOGITS
    .".
    0.77
    .")
    0.72
    ري
    0.71
    .”.
    0.71
    .')
    0.70
    ऑक्साइड
    0.70
     materialize
    0.69
     inning
    0.68
    .​​
    0.66
    rinth
    0.66
    Activations Density 0.003%

    No Known Activations