© 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-262K
    7. 10698
    Prev
    Next
    INDEX
    Explanations

    multiple [models, marriages, ... ]

    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_262k_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
    se
    2.17
    liche
    1.95
    )=>{
    1.94
    ilm
    1.90
    lichen
    1.86
    不住
    1.83
    निया
    1.82
    urile
    1.81
    м
    1.80
    ん
    1.79
    POSITIVE LOGITS
     sclerosis
    3.47
     myeloma
    3.14
     trava
    1.83
     universes
    1.76
     hearsay
    1.75
    篁
    1.70
    тесь
    1.69
     gallons
    1.67
     Пла
    1.66
     calorías
    1.66
    Activations Density 0.134%

    No Known Activations