© 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. 83737
    Prev
    Next
    INDEX
    Explanations

    health, social, and technical contexts

    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
     Hand
    0.50
    ぜ
    0.49
     Solar
    0.48
     solar
    0.47
     K
    0.46
     hurricane
    0.45
     Ні
    0.44
    ฤ
    0.44
     provided
    0.44
     И
    0.43
    POSITIVE LOGITS
    कांना
    0.54
    convert
    0.52
    asshi
    0.52
     विद्यार्थ्यांना
    0.51
    acchati
    0.50
    otricha
    0.48
    reactant
    0.47
     திரும்ப
    0.47
     പ്രതീ
    0.46
     جاسک
    0.46
    Activations Density 0.002%

    No Known Activations