© 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. 2302
    Prev
    Next
    INDEX
    Explanations

    HTML, CSS, JavaScript

    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
     народу
    -0.87
     κ
    -0.85
     iko
    -0.78
    Plen
    -0.76
    Typ
    -0.76
     된
    -0.75
     €/
    -0.74
     σα
    -0.73
     amyloid
    -0.73
    Gav
    -0.72
    POSITIVE LOGITS
    gsub
    0.90
     Anzeige
    0.88
    cation
    0.88
     MessageBoxIcon
    0.86
    endida
    0.86
    蓠
    0.84
    mousemove
    0.84
     apoi
    0.84
    vanta
    0.83
    mtext
    0.83
    Activations Density 0.004%

    No Known Activations