© 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-16K
    7. 7780
    Prev
    Next
    INDEX
    Explanations

    paths and technical terms

    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_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
    uz
    0.72
    з
    0.71
     basic
    0.70
    І
    0.68
    olate
    0.67
     ло
    0.66
    oc
    0.65
    oche
    0.65
    وی
    0.65
     щ
    0.65
    POSITIVE LOGITS
     oferecer
    0.97
     reduzir
    0.89
     Bamber
    0.88
     analisar
    0.88
     Gonçalves
    0.87
     būti
    0.86
     tiveram
    0.85
    ﻕ
    0.85
     Morel
    0.84
     учены
    0.84
    Activations Density 0.000%

    No Known Activations