© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 11960
    Prev
    Next
    INDEX
    Explanations

    email headers and scientific terms

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

    email format elements like "From:", "To:", "Subject:", and timestamps in email headers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    يارات
    -0.85
     transporta
    -0.81
    ksjoner
    -0.79
    
    -0.78
    нему
    -0.77
     áreas
    -0.75
     öğren
    -0.75
    Perhaps
    -0.75
    setCursor
    -0.74
    및
    -0.74
    POSITIVE LOGITS
     zeich
    0.86
     präsenti
    0.86
     perdere
    0.85
    这张
    0.85
    ច
    0.84
     peixes
    0.82
     elegant
    0.80
    怎么做
    0.79
     カップ
    0.78
     blazing
    0.77
    Activations Density 0.001%

    No Known Activations