© 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. 12-GEMMASCOPE-2-RES-16K
    7. 12452
    Prev
    Next
    INDEX
    Explanations

    practices, styles, training, optimization

    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_12_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
    少し
    0.84
     pathologies
    0.82
    埤
    0.82
    ig
    0.81
    陂
    0.80
     arbeids
    0.80
    ផ្សេង
    0.78
    ્ષ
    0.78
     زیادی
    0.78
     landslides
    0.77
    POSITIVE LOGITS
    .
    1.17
    :
    0.99
    ;
    0.84
    !
    0.75
    ){
    0.72
    ?
    0.71
    UK
    0.71
    ™,
    0.71
    ESA
    0.70
    ,
    0.70
    Activations Density 1.540%

    No Known Activations