© 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. 73715
    Prev
    Next
    INDEX
    Explanations

    contact, identity, information, access

    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
     still
    -1.20
     hardly
    -1.07
     already
    -1.07
     چربی
    -1.02
     all
    -1.02
     Augenblick
    -1.01
    :
    -0.99
     it
    -0.98
     administração
    -0.94
     S
    -0.94
    POSITIVE LOGITS
     якщо
    1.41
    你可以
    1.31
     you
    1.31
     chiedere
    1.31
     если
    1.30
     إذا
    1.27
    য়া
    1.23
    如果你
    1.22
    あなたが
    1.20
     اگر
    1.20
    Activations Density 0.003%

    No Known Activations