© 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. 347
    Prev
    Next
    INDEX
    Explanations

    to + verb or noun

    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
     if
    -1.75
    Surprisingly
    -1.46
    氾
    -1.41
    Everything
    -1.41
     provides
    -1.35
    Just
    -1.31
    All
    -1.31
     this
    -1.30
     helps
    -1.28
    What
    -1.27
    POSITIVE LOGITS
    necessarily
    1.45
    <tr>
    1.40
    螃
    1.35
     effectué
    1.34
    嚒
    1.31
    摸了
    1.30
     छोड़
    1.29
     asfal
    1.29
     appelée
    1.27
     associée
    1.26
    Activations Density 0.017%

    No Known Activations