© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 51187
    Prev
    Next
    INDEX
    Explanations

    discourse markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    ี
    0.56
    US
    0.54
    u
    0.52
     moles
    0.47
     Blogger
    0.46
     Mole
    0.46
     US
    0.45
    ่า
    0.45
    mole
    0.45
     Lawyers
    0.43
    POSITIVE LOGITS
    MinIntensity
    0.55
    avacanam
    0.50
    ivasena
    0.47
     vajj
    0.44
     [§
    0.44
     تھا۔
    0.43
    ዋል።
    0.43
    istocene
    0.43
     اكيد
    0.43
    avaient
    0.42
    Activations Density 0.000%

    No Known Activations