© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65023
    Prev
    Next
    INDEX
    Explanations

    discuss or talk about

    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
     blanches
    -1.06
    idorm
    -0.99
     навіть
    -0.99
     соціаль
    -0.99
    很多的
    -0.97
     useRouter
    -0.96
     descendre
    -0.96
    nachweis
    -0.94
    ordes
    -0.94
     censiti
    -0.94
    POSITIVE LOGITS
     why
    2.70
     how
    2.31
     being
    2.14
     his
    2.11
     what
    1.74
     challenges
    1.55
     having
    1.42
     their
    1.41
    为什么
    1.37
     lessons
    1.36
    Activations Density 0.048%

    No Known Activations