© 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. 107521
    Prev
    Next
    INDEX
    Explanations

    domain classification

    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
     certamente
    -0.97
    BASELINE
    -0.92
    ϫ
    -0.91
     fokus
    -0.85
     измени
    -0.83
     ».
    -0.82
    лос
    -0.82
     kalangan
    -0.81
     ofrecemos
    -0.81
    кономи
    -0.81
    POSITIVE LOGITS
     setup
    1.53
     SetUp
    1.18
     as
    1.16
    setup
    1.13
     aspects
    1.12
     Setup
    1.09
     aspect
    1.07
     activities
    1.00
    واد
    0.99
     and
    0.98
    Activations Density 0.036%

    No Known Activations