© 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. 10-GEMMASCOPE-RES-131K
    7. 130714
    Prev
    Next
    INDEX
    Explanations

    malaria or malarial

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

    court case citations with year and document numbers.

    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_10/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
     since
    -1.70
     H
    -1.63
     We
    -1.63
     $
    -1.53
     has
    -1.53
     If
    -1.50
     hacer
    -1.48
     Since
    -1.47
    !
    -1.46
        
    -1.45
    POSITIVE LOGITS
     indeks
    1.76
    饜
    1.64
     drame
    1.61
    
    1.60
     bestem
    1.55
     maksi
    1.51
     verborgen
    1.44
     organisme
    1.43
    めで
    1.42
    -¡
    1.41
    Activations Density 0.035%

    No Known Activations