© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15094
    Prev
    Next
    INDEX
    Explanations

    catch (error)

    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_31_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
    REST
    0.68
    Hopefully
    0.62
    Den
    0.61
    adin
    0.60
    DR
    0.59
    Ch
    0.59
    J
    0.59
    Convert
    0.59
    Hope
    0.58
    hope
    0.57
    POSITIVE LOGITS
     accelerating
    0.68
     выбра
    0.58
     Skins
    0.54
    ▉
    0.53
     Gambar
    0.52
     aceler
    0.52
     productId
    0.51
     පො
    0.51
     accél
    0.51
     Bartlett
    0.50
    Activations Density 0.017%

    No Known Activations