© 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. 97896
    Prev
    Next
    INDEX
    Explanations

    technical terms and names

    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
     theme
    -0.99
     Retina
    -0.91
    THEME
    -0.90
    theme
    -0.90
     gør
    -0.90
    ኝ
    -0.88
     ホット
    -0.85
    ▐
    -0.85
     forsø
    -0.85
     THEME
    -0.85
    POSITIVE LOGITS
    surf
    0.76
     surface
    0.75
    Zar
    0.73
     поверх
    0.69
     વા
    0.68
    SURFACE
    0.68
    Guild
    0.68
     jay
    0.68
    Surface
    0.67
    Surf
    0.67
    Activations Density 0.004%

    No Known Activations