© 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. 1177
    Prev
    Next
    INDEX
    Explanations

    privileges or privilege escalation

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

    paragraph breaks or transitions between distinct news articles or sections in a document.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     poils
    -1.65
    
    -1.64
    냑
    -1.61
    这般
    -1.50
     Responsable
    -1.49
     recuperação
    -1.48
     mauva
    -1.46
    锲
    -1.46
    UMMY
    -1.44
     spektak
    -1.44
    POSITIVE LOGITS
     when
    1.76
     izvē
    1.72
     вси
    1.70
     ikke
    1.63
     or
    1.63
    /
    1.63
    We
    1.56
     møte
    1.55
    ですが
    1.55
     samarbeid
    1.54
    Activations Density 0.405%

    No Known Activations