© 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. 106764
    Prev
    Next
    INDEX
    Explanations

    well- adjectives

    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
     fragile
    -0.90
    ként
    -0.87
    tellungs
    -0.85
     relevan
    -0.84
     competitively
    -0.79
    Shown
    -0.79
    脆弱
    -0.79
    ⚬
    -0.78
    дом
    -0.77
    coque
    -0.77
    POSITIVE LOGITS
     equipped
    1.42
     organized
    1.35
     behaved
    1.17
     organised
    1.14
     educated
    1.13
     funded
    1.11
     rounded
    1.11
     suited
    1.07
     connected
    1.05
     balanced
    1.03
    Activations Density 0.041%

    No Known Activations