© 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. 91075
    Prev
    Next
    INDEX
    Explanations

    HTML tags and code blocks

    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
     access
    -1.18
    access
    -0.96
     toegang
    -0.86
     accessing
    -0.85
    アクセス
    -0.84
    Access
    -0.80
     Access
    -0.80
    塾
    -0.80
     acceder
    -0.78
    AccessType
    -0.78
    POSITIVE LOGITS
    dequeue
    0.97
     Arc
    0.90
    emore
    0.84
     embedding
    0.83
     Identity
    0.81
     centrum
    0.78
     cosine
    0.78
    Schöne
    0.77
     cos
    0.77
    Contras
    0.77
    Activations Density 0.011%

    No Known Activations