© 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. 33243
    Prev
    Next
    INDEX
    Explanations

    dependent variable

    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
     අවශ්‍ය
    0.52
    car
    0.45
     
    0.45
     helper
    0.44
    鐳
    0.44
    tr
    0.43
    texto
    0.43
    निम्नलिखित
    0.43
     Router
    0.42
     অনুরূপ
    0.42
    POSITIVE LOGITS
    当时
    0.50
    $).
    0.47
    ່
    0.45
    當時
    0.44
    доль
    0.42
     protests
    0.41
    Despite
    0.41
     đương
    0.41
    当時
    0.41
    Walk
    0.41
    Activations Density 0.006%

    No Known Activations