© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16282
    Prev
    Next
    INDEX
    Explanations

    to solve

    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
    汽车
    0.62
     airplanes
    0.61
     নিয়
    0.60
     animals
    0.59
    boats
    0.59
    ઞ
    0.59
     নিয়
    0.58
     bicycles
    0.58
    並且
    0.57
    安心
    0.57
    POSITIVE LOGITS
     ChIP
    0.61
     Sticky
    0.61
     Deduction
    0.54
     Headlines
    0.54
     ROOT
    0.53
     sticky
    0.52
    <unused31>
    0.52
     deductible
    0.52
     yolks
    0.52
     CAGR
    0.50
    Activations Density 0.326%

    No Known Activations