© 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. 5515
    Prev
    Next
    INDEX
    Explanations

    maths, functions, passwords, routes, thinner

    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
     cousins
    0.73
    ៗ
    0.71
     cavalry
    0.68
     บน
    0.68
    ᚨ
    0.68
     premiered
    0.66
     heyday
    0.66
    '
    0.66
     whence
    0.65
     announced
    0.65
    POSITIVE LOGITS
    関節
    0.74
     ನೀಡ
    0.71
    あなた
    0.70
     zaradi
    0.69
     Incorpor
    0.67
     Equilib
    0.67
    悩
    0.67
    marshalO
    0.66
    equilib
    0.66
     bunları
    0.65
    Activations Density 0.000%

    No Known Activations