© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15897
    Prev
    Next
    INDEX
    Explanations

    he said or she said

    np_acts-logits-general · gemini-2.5-flash-lite

    reporting speech or information

    np_acts-logits-general · gemini-2.5-flash-lite

    sentence continuation

    np_max-act · claude-4-5-sonnetTriggered by @sk5695

    punctuation

    np_max-act-logits · claude-4-5-sonnetTriggered by @sripadkarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ہم
    0.53
    வதும்
    0.44
    这是
    0.42
    
    0.40
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.40
    屡
    0.39
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.39
    ↵↵↵
    0.38
     جذ
    0.38
    Forward
    0.38
    POSITIVE LOGITS
    他說
    1.23
    他说
    1.20
    她说
    1.00
    他还
    0.93
     kwamba
    0.82
     bahwa
    0.81
    他对
    0.81
     noting
    0.80
     rằng
    0.80
    他又
    0.80
    Activations Density 0.383%

    No Known Activations