© 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. 17794
    Prev
    Next
    INDEX
    Explanations

    indicates causes for issues

    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
     стимули
    0.42
    
    0.39
    icultural
    0.39
    үнд
    0.38
    STRAINT
    0.38
    色彩
    0.37
    Basil
    0.37
    充分
    0.37
    燥
    0.36
    >,</
    0.35
    POSITIVE LOGITS
     former
    0.48
     cũ
    0.47
     wc
    0.46
     mantan
    0.44
     Arkansas
    0.43
     Belarus
    0.43
     tracker
    0.42
     keres
    0.42
     rc
    0.42
     মেয়াদ
    0.42
    Activations Density 0.001%

    No Known Activations