© 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. 58376
    Prev
    Next
    INDEX
    Explanations

    Convergence of, Along with

    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
     tubs
    -0.72
     tourist
    -0.66
     Extension
    -0.65
    Ext
    -0.65
    jestic
    -0.62
    Њ
    -0.62
    Designs
    -0.62
     extension
    -0.61
     Mediterranean
    -0.61
     Japanese
    -0.60
    POSITIVE LOGITS
     cerim
    0.76
     relata
    0.75
    rufe
    0.74
    ッソ
    0.74
     魚
    0.74
     cleanliness
    0.73
    viamente
    0.72
    cole
    0.71
    قبال
    0.71
     雪
    0.70
    Activations Density 0.047%

    No Known Activations