© 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. 76088
    Prev
    Next
    INDEX
    Explanations

    {{ name }} / Employee Dimension / polyurea

    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
    メーカー
    0.50
    ድግዳ
    0.44
    Volt
    0.42
    バス
    0.42
    그
    0.42
    Ki
    0.41
    AMIN
    0.41
    ﺍ
    0.41
     strokes
    0.41
    レー
    0.40
    POSITIVE LOGITS
    0
    0.50
     murderous
    0.47
     ಅದನ್ನು
    0.47
     പരിച
    0.46
    𝟎
    0.45
     инг
    0.45
    pageY
    0.44
    andr
    0.43
    వంటి
    0.42
    砓
    0.42
    Activations Density 0.001%

    No Known Activations