© 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. 14107
    Prev
    Next
    INDEX
    Explanations

    access to, sale of, risk of

    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
     این
    -1.27
     tämän
    -1.17
     กรัม
    -1.11
    Ｍ
    -1.06
    雖
    -1.05
     letzten
    -1.03
     This
    -1.02
     denna
    -1.00
     инструкция
    -1.00
     сами
    -0.99
    POSITIVE LOGITS
     in
    1.73
     of
    1.41
    もあって
    1.26
    Stun
    1.09
    ですが
    1.09
    Exeunt
    1.09
     フィギュア
    1.05
    などは
    1.04
     نیروهای
    1.04
     persons
    1.03
    Activations Density 0.131%

    No Known Activations