© 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. 25981
    Prev
    Next
    INDEX
    Explanations

    bin/ paths

    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
     GetComponent
    -0.80
    COOH
    -0.78
    mountable
    -0.77
     artifice
    -0.73
     конструкция
    -0.73
    patrón
    -0.72
     dormitórios
    -0.72
     inductive
    -0.70
     Werbung
    -0.70
     ఉ
    -0.70
    POSITIVE LOGITS
    ◖
    0.91
     pö
    0.87
    still
    0.86
    tersebut
    0.83
    żenia
    0.81
    highlighted
    0.80
    reifen
    0.80
    WiFi
    0.80
     raken
    0.80
    becomes
    0.79
    Activations Density 0.050%

    No Known Activations