© 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. 67431
    Prev
    Next
    INDEX
    Explanations

    data structure operations

    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
     not
    -0.95
     both
    -0.91
     preoccupation
    -0.91
     first
    -0.89
     about
    -0.86
     four
    -0.85
     before
    -0.84
     some
    -0.81
     Both
    -0.80
     changing
    -0.79
    POSITIVE LOGITS
     its
    1.06
    ものです
    1.05
    íts
    1.01
     rhestr
    1.00
    ArrowToggle
    0.92
    🅓
    0.91
     innerhalb
    0.88
     parfois
    0.88
    它的
    0.88
    Preço
    0.85
    Activations Density 0.049%

    No Known Activations