© 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. 40-GEMMASCOPE-2-RES-262K
    7. 134137
    Prev
    Next
    INDEX
    Explanations

    efficient generalization

    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_40_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
    送到
    0.41
    としている
    0.41
    ꩡ
    0.38
    践
    0.38
    后再
    0.38
    ScienceStudent
    0.37
     пост
    0.37
    創造
    0.37
    锰
    0.37
    
    0.36
    POSITIVE LOGITS
     LR
    0.48
     LE
    0.44
     tens
    0.43
     authorized
    0.43
     pars
    0.43
     ding
    0.42
    rist
    0.42
     CA
    0.41
    ding
    0.41
     JA
    0.41
    Activations Density 0.000%

    No Known Activations