© 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. 11067
    Prev
    Next
    INDEX
    Explanations

    people and their items

    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
     you
    -0.89
     obligaciones
    -0.87
     verdaderamente
    -0.84
     Cervical
    -0.84
     your
    -0.84
     >
    -0.83
    𝐗
    -0.82
    对
    -0.82
    指甲
    -0.81
    iconque
    -0.81
    POSITIVE LOGITS
     their
    1.78
     they
    1.75
     mereka
    1.45
     ihnen
    1.43
     ihrer
    1.38
     themselves
    1.38
     Mereka
    1.26
    给他们
    1.21
    他们
    1.12
    themselves
    1.08
    Activations Density 0.137%

    No Known Activations