© 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. 71234
    Prev
    Next
    INDEX
    Explanations

    beginning or starting something

    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
    already
    -1.21
    Already
    -1.10
    áciu
    -1.07
     is
    -1.07
     noiembrie
    -1.01
    現貨
    -1.00
    If
    -0.99
     already
    -0.98
    已经
    -0.98
    essayer
    -0.97
    POSITIVE LOGITS
     started
    1.66
     began
    1.57
     came
    1.35
     first
    1.27
     became
    1.20
    เริ่ม
    1.18
     idea
    1.13
     this
    1.10
     start
    1.09
     böyle
    1.07
    Activations Density 0.039%

    No Known Activations