© 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. 34-GEMMASCOPE-RES-131K
    7. 117925
    Prev
    Next
    INDEX
    Explanations

    code paths and beginnings of URLs

    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
     Once
    -0.87
     Sometimes
    -0.81
    Sometimes
    -0.81
     intricate
    -0.79
     this
    -0.79
    tomy
    -0.78
     intricacies
    -0.77
     one
    -0.76
     precise
    -0.76
     Besides
    -0.75
    POSITIVE LOGITS
     comunes
    0.98
     dentes
    0.98
    ushka
    0.95
    ondes
    0.89
     célèbre
    0.89
     Supplements
    0.89
     amazingly
    0.89
     PERSON
    0.89
     STORY
    0.88
    杢
    0.88
    Activations Density 0.016%

    No Known Activations