© 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. 5992
    Prev
    Next
    INDEX
    Explanations

    base model / básicamente

    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
    </iframe>
    0.61
     División
    0.61
     Sari
    0.59
    녓
    0.59
    iado
    0.58
     महासचिव
    0.57
    iul
    0.57
     दक्षिणी
    0.56
    edik
    0.56
    hou
    0.56
    POSITIVE LOGITS
     premise
    0.71
    stoke
    0.71
    ស្ថាន
    0.68
     Base
    0.64
    camp
    0.64
    भूत
    0.64
     отдыха
    0.63
     깔
    0.63
     बातों
    0.63
     ganglia
    0.62
    Activations Density 0.231%

    No Known Activations