© 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. 118423
    Prev
    Next
    INDEX
    Explanations

    evidence and communication records

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    newsletter
    -1.01
     keten
    -0.89
    🍒
    -0.88
    ⟹
    -0.88
    yaa
    -0.88
    🏈
    -0.88
    dollars
    -0.88
    ofas
    -0.88
    вку
    -0.87
     merke
    -0.86
    POSITIVE LOGITS
     phone
    1.75
     telephone
    1.45
     statements
    1.39
     DNA
    1.38
     witnesses
    1.37
     evidence
    1.35
     video
    1.35
     audio
    1.34
     emails
    1.34
     cell
    1.27
    Activations Density 0.030%

    No Known Activations