© 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-16K
    4. 9317
    Prev
    Next
    INDEX
    Explanations

    academic citations and technical identifiers

    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_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
    <sup>
    0.38
     čini
    0.36
     Pham
    0.36
      
    0.35
     stammt
    0.35
    »,
    0.34
    вле
    0.34
     pregi
    0.34
     Tra
    0.33
     আরবি
    0.33
    POSITIVE LOGITS
    ჯგუფი
    0.39
    blockSize
    0.37
    𒋛
    0.35
     loadAnimation
    0.35
    ండా
    0.35
    shaders
    0.35
     murderers
    0.35
    硖
    0.34
     giants
    0.33
    很难
    0.33
    Activations Density 0.097%

    No Known Activations