© 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. 39804
    Prev
    Next
    INDEX
    Explanations

    proposed or planned actions

    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
    hány
    -1.05
     is
    -0.96
     favoris
    -0.91
     hivyo
    -0.91
     tonel
    -0.91
     kanilang
    -0.86
     are
    -0.85
    峮
    -0.84
     trebuie
    -0.84
     precisam
    -0.84
    POSITIVE LOGITS
     would
    2.98
     was
    1.78
     hätte
    1.76
    would
    1.61
     had
    1.58
     wäre
    1.55
    Would
    1.52
     Would
    1.50
     planned
    1.49
     proposed
    1.46
    Activations Density 0.076%

    No Known Activations