© 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. 9749
    Prev
    Next
    INDEX
    Explanations

    tax optimization strategies

    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
     Stunning
    0.77
     Invention
    0.71
    话题
    0.70
    ч
    0.70
     Document
    0.70
     С
    0.68
     О
    0.67
     stunning
    0.67
     کہنے
    0.66
     Հ
    0.66
    POSITIVE LOGITS
     inférieures
    0.86
     supérieures
    0.86
    ین
    0.83
     situés
    0.82
     effectuées
    0.81
     precipitates
    0.78
    charges
    0.77
    टर
    0.77
    कौन
    0.77
    ванням
    0.76
    Activations Density 0.001%

    No Known Activations