© 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. 22-GEMMASCOPE-RES-131K
    7. 14369
    Prev
    Next
    INDEX
    Explanations

    legal or mathematical 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_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
     pieniądze
    -1.02
    tembro
    -1.02
     poder
    -1.02
     это
    -0.99
    //{
    -0.98
    呜
    -0.96
     tym
    -0.96
     For
    -0.94
    渽
    -0.94
     gwaran
    -0.92
    POSITIVE LOGITS
    lowns
    1.11
     oplossing
    1.09
     asisten
    1.06
     国家
    1.03
    uterine
    1.02
     juſ
    0.99
    <bos>
    0.99
    ristmas
    0.96
     universitaria
    0.95
    珢
    0.94
    Activations Density 0.065%

    No Known Activations