© 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. 98195
    Prev
    Next
    INDEX
    Explanations

    code blocks, variable assignments, and control flow

    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
    Transkript
    -1.12
    Transcripción
    -1.11
    /**
    -1.03
    Transcriptie
    -1.00
    URBANA
    -0.97
    谞
    -0.97
    Modo
    -0.95
    OLEAN
    -0.93
    
    -0.91
    Zin
    -0.88
    POSITIVE LOGITS
    JButton
    0.99
     vielmehr
    0.99
     accesorios
    0.99
     denselben
    0.98
    Row
    0.98
     almacen
    0.97
     verschied
    0.96
    group
    0.95
    @[+][
    0.94
     einzelne
    0.94
    Activations Density 0.008%

    No Known Activations