© 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. 28707
    Prev
    Next
    INDEX
    Explanations

    data structures and programming terms

    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
     you
    0.54
    2
    0.51
    i
    0.49
    ur
    0.48
     sarees
    0.47
     with
    0.47
    ش
    0.47
    ج
    0.46
     Σ
    0.45
     Gao
    0.44
    POSITIVE LOGITS
    
    0.55
    ️
    0.50
     산
    0.50
    ле
    0.48
     개념
    0.47
    ის
    0.47
     или
    0.47
    но
    0.46
     பெரும்பாலான
    0.45
    이나
    0.45
    Activations Density 0.235%

    No Known Activations