© 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-262K
    7. 7704
    Prev
    Next
    INDEX
    Explanations

    combined use of information or actions

    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_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
    ;
    0.73
     для
    0.72
    ర్‌లో
    0.71
     עבור
    0.69
     когда
    0.68
     потому
    0.68
    。
    0.67
     für
    0.66
     چاہیے۔
    0.66
     گئی۔
    0.65
    POSITIVE LOGITS
     ،
    0.80
     circumstances
    0.77
     judicious
    0.75
     circonstances
    0.72
    combined
    0.71
     précédentes
    0.70
     وبا
    0.69
     combined
    0.69
     السنوات
    0.68
     combination
    0.68
    Activations Density 0.002%

    No Known Activations