© 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. 10-GEMMASCOPE-RES-131K
    7. 19308
    Prev
    Next
    INDEX
    Explanations

    instructions in code comments

    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_10/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
     betale
    -1.34
    और
    -1.30
    pography
    -1.25
     bús
    -1.19
     spada
    -1.18
     obiet
    -1.16
     politika
    -1.15
    粜
    -1.15
     turista
    -1.15
    cej
    -1.15
    POSITIVE LOGITS
    xelles
    1.27
    badah
    1.22
     \(
    1.21
    ником
    1.19
    онов
    1.16
     también
    1.16
    ний
    1.16
    paco
    1.15
    )}+
    1.15
     It
    1.15
    Activations Density 0.067%

    No Known Activations