© 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. 2699
    Prev
    Next
    INDEX
    Explanations

    spent time, spent hours, spent days

    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
    -
    0.92
    .
    0.89
    '
    0.81
     you
    0.78
    0.75
     they
    0.73
    :
    0.71
     '
    0.68
    אם
    0.68
     section
    0.67
    POSITIVE LOGITS
    arankan
    0.79
    udahkan
    0.75
    য়েছে
    0.71
     Органи
    0.66
    ademie
    0.65
    শংস
    0.64
    忶
    0.64
    蔫
    0.63
    ल्ट
    0.63
     પ્રે
    0.62
    Activations Density 0.009%

    No Known Activations