© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113796
    Prev
    Next
    INDEX
    Explanations

    setting html content

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

    the `.html()` method in jQuery/JavaScript code.

    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
    されていない
    -1.82
    
    -1.50
    calça
    -1.48
    
    -1.45
     hulle
    -1.43
    🫴
    -1.38
     own
    -1.38
    certain
    -1.37
     mereka
    -1.36
     redan
    -1.35
    POSITIVE LOGITS
     hiciera
    1.40
     capabilities
    1.37
    太
    1.36
    どういう
    1.29
    ;
    1.29
    太好了
    1.28
    というわけで
    1.27
    了一
    1.27
     autorisés
    1.27
     After
    1.25
    Activations Density 0.005%

    No Known Activations