© 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. 9429
    Prev
    Next
    INDEX
    Explanations

    mathematical problems and statements

    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
     five
    -1.20
     From
    -1.12
     reinforces
    -1.11
     eight
    -1.11
     nine
    -1.05
     exuberant
    -1.05
     six
    -1.05
     several
    -1.05
    -
    -1.04
     three
    -1.03
    POSITIVE LOGITS
     protoimpl
    1.13
     significativo
    1.12
     purpoſe
    1.10
    ushes
    1.08
     crea
    1.05
    甚至
    1.05
    ’
    1.05
    の中では
    1.03
    銆
    1.03
     عدد
    1.02
    Activations Density 0.041%

    No Known Activations