© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 126300
    Prev
    Next
    INDEX
    Explanations

    open weights available

    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
    ,’
    0.48
    𝘁
    0.46
    ický
    0.45
    ,”
    0.43
    geschossiges
    0.42
    ,'
    0.41
    ве
    0.41
    ocular
    0.41
    |,
    0.41
     earnestly
    0.41
    POSITIVE LOGITS
     campes
    0.52
     khand
    0.48
    checkBox
    0.47
     kent
    0.46
     carreras
    0.46
     zast
    0.45
     村
    0.45
     रजि
    0.45
     kamp
    0.44
    畋
    0.44
    Activations Density 0.002%

    No Known Activations