© 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. 116616
    Prev
    Next
    INDEX
    Explanations

    payment, licensed, collected

    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
     awakened
    -0.86
     INSPECTION
    -0.79
     Shiraz
    -0.76
    gray
    -0.74
     Vip
    -0.73
    ürzt
    -0.72
     knex
    -0.71
    goe
    -0.71
     ZEALAND
    -0.70
     Salts
    -0.69
    POSITIVE LOGITS
     оке
    0.81
     зробити
    0.78
    忘
    0.72
    Commissioner
    0.69
    ecs
    0.69
     Commissioner
    0.69
    ORCID
    0.69
    CFG
    0.69
     ADI
    0.69
    Werdegang
    0.69
    Activations Density 0.003%

    No Known Activations