© 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-65K
    7. 14559
    Prev
    Next
    INDEX
    Explanations

    instructions and descriptions

    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_65k_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
     fenómeno
    0.48
     fenô
    0.45
     fenómenos
    0.44
    
    0.43
     melamine
    0.43
     chủng
    0.43
     polyethylene
    0.42
     movement
    0.42
    原料
    0.41
    面
    0.41
    POSITIVE LOGITS
     This
    0.47
     So
    0.44
    aq
    0.44
     ر
    0.43
    Sparse
    0.42
    putation
    0.42
    maintain
    0.42
    lar
    0.41
    could
    0.40
    voll
    0.40
    Activations Density 0.007%

    No Known Activations