© 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. 116640
    Prev
    Next
    INDEX
    Explanations

    hash tables

    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
    JsonPropertyName
    -0.87
     σο
    -0.85
    ༺
    -0.77
     Shields
    -0.77
     Frankie
    -0.75
     ModelExpression
    -0.75
     PBS
    -0.75
    囚
    -0.74
    ਪ
    -0.73
     sank
    -0.73
    POSITIVE LOGITS
     table
    2.64
     tables
    2.20
    table
    2.08
    Table
    2.02
     hash
    1.89
     Table
    1.85
     табли
    1.67
     Tables
    1.67
    HashTable
    1.64
     Hash
    1.61
    Activations Density 0.073%

    No Known Activations