© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 102669
    Prev
    Next
    INDEX
    Explanations

    court cases and technical terms

    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
    وج
    -0.75
    sf
    -0.74
     Personen
    -0.73
    าด
    -0.73
     back
    -0.69
    ્ય
    -0.68
    érc
    -0.68
    ーション
    -0.67
     strong
    -0.67
     maximize
    -0.66
    POSITIVE LOGITS
    一样的
    0.70
     $?
    0.69
    IDEN
    0.69
    

    0.69
     Flamengo
    0.68
     SRL
    0.68
     المل
    0.68
    MMS
    0.67
     TTL
    0.65
     irrig
    0.65
    Activations Density 0.060%

    No Known Activations