© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8385
    Prev
    Next
    INDEX
    Explanations

    programming keywords and operations

    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
    <unused2169>
    0.82
    <unused2164>
    0.80
    <unused2110>
    0.80
    <unused2173>
    0.80
    <unused2157>
    0.79
    <unused2223>
    0.72
    <unused2172>
    0.71
    <unused2117>
    0.70
    <unused2137>
    0.70
    <unused2121>
    0.70
    POSITIVE LOGITS
    Prior
    0.69
    Pro
    0.66
     Prior
    0.65
    Core
    0.65
    Lever
    0.65
    Lisa
    0.62
     Divers
    0.62
    Q
    0.62
    New
    0.61
    Score
    0.61
    Activations Density 0.137%

    No Known Activations