© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13898
    Prev
    Next
    INDEX
    Explanations

    email address or format

    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
    膝
    0.61
     Tissue
    0.60
    Tissue
    0.57
     আফ
    0.54
     અધ
    0.53
    constraintTop
    0.52
    隆
    0.52
    cnc
    0.51
     ऑक्सीजन
    0.51
    烃
    0.50
    POSITIVE LOGITS
     mail
    1.45
     Mail
    1.41
     Gmail
    1.41
    邮件
    1.41
     mails
    1.41
     MAIL
    1.41
    Mail
    1.40
    Gmail
    1.38
     emails
    1.37
     mailbox
    1.37
    Activations Density 0.184%

    No Known Activations