© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1876
    Prev
    Next
    INDEX
    Explanations

    tax exemptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     matri
    1.11
    asibility
    1.06
     feasts
    1.02
    {
    0.96
    iatric
    0.95
     leader
    0.94
     eens
    0.93
    verse
    0.91
    idental
    0.90
     midwife
    0.88
    POSITIVE LOGITS
    exempt
    2.08
     evasion
    2.05
     exemptions
    2.02
     exemption
    2.00
    ريبا
    1.96
    磴
    1.96
     exempted
    1.95
     Exempt
    1.93
    әп
    1.93
    iviato
    1.91
    Activations Density 0.122%

    No Known Activations