© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129440
    Prev
    Next
    INDEX
    Explanations

    legal, scientific, or literary 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
    瞩
    -0.94
    骇
    -0.90
    ipe
    -0.89
     pungkas
    -0.88
     Mian
    -0.87
    喫茶
    -0.87
    nexo
    -0.87
    生まれた
    -0.86
     inapropiados
    -0.86
    一丝
    -0.84
    POSITIVE LOGITS
     experts
    1.20
    ְּ
    1.11
    siye
    1.05
     lustig
    1.04
     befindet
    1.02
     Experts
    1.02
     蓋
    1.02
    дання
    1.00
     spoke
    1.00
     Tuesday
    1.00
    Activations Density 0.001%

    No Known Activations