© 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. 8148
    Prev
    Next
    INDEX
    Explanations

    json structure or code blocks

    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
     '/
    0.71
     '/',
    0.70
     '{
    0.68
     定义
    0.66
    如下
    0.65
     (),
    0.64
     '*',
    0.64
    ಹಿತ
    0.63
     คณิต
    0.61
    ),]),
    0.61
    POSITIVE LOGITS
    Original
    0.55
    FIS
    0.54
    responsible
    0.53
    섬
    0.53
    council
    0.52
    hebung
    0.52
    uld
    0.51
    ۢ
    0.51
     accountable
    0.51
    ధి
    0.51
    Activations Density 0.201%

    No Known Activations