© 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. 34-GEMMASCOPE-RES-131K
    7. 103720
    Prev
    Next
    INDEX
    Explanations

    geometric form and edges

    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
     美人
    -0.87
    voyer
    -0.85
    Conteúdo
    -0.84
    ğmen
    -0.81
     Valhalla
    -0.80
    ibrator
    -0.80
     possibilités
    -0.79
    لز
    -0.79
     Horiz
    -0.79
    assemb
    -0.79
    POSITIVE LOGITS
     profile
    1.09
     cham
    1.05
     face
    1.02
     transitions
    1.02
     undercut
    1.01
     edge
    0.98
     shoulders
    0.98
     transitioned
    0.95
     faces
    0.94
     facets
    0.94
    Activations Density 0.069%

    No Known Activations