© 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. 123960
    Prev
    Next
    INDEX
    Explanations

    purpose "so that" clauses

    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
     dieß
    -1.58
     tiveram
    -1.48
     emballage
    -1.45
    
    -1.45
     trabalhadores
    -1.45
     tradisi
    -1.45
    ♱
    -1.42
     विश्वसनीयता
    -1.34
    passen
    -1.33
    wendige
    -1.32
    POSITIVE LOGITS
    2
    1.92
    4
    1.66
     be
    1.48
    7
    1.47
     folds
    1.43
     beasts
    1.41
    *
    1.36
    3
    1.34
    :
    1.32
    ሖ
    1.32
    Activations Density 0.019%

    No Known Activations