© 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. 22-GEMMASCOPE-RES-131K
    7. 36437
    Prev
    Next
    INDEX
    Explanations

    specific formatting or structure

    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_22/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
     سایر
    -0.93
    imbang
    -0.88
    UFACT
    -0.86
    britannien
    -0.85
     jao
    -0.84
     börjar
    -0.83
     cuillère
    -0.83
    жели
    -0.83
     those
    -0.82
     on
    -0.82
    POSITIVE LOGITS
    latter
    1.01
     gefahren
    0.99
     gegangen
    0.95
    affected
    0.90
    imenti
    0.90
    𝑛
    0.90
     interesado
    0.88
     eax
    0.88
     прошлого
    0.87
    Something
    0.87
    Activations Density 0.003%

    No Known Activations