© 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. 42525
    Prev
    Next
    INDEX
    Explanations

    words ending in fully

    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
    硨
    -2.70
    ޢ
    -2.48
     hanem
    -2.23
     Ensuring
    -2.05
    わりに
    -2.02
     Intense
    -2.02
    стандарт
    -2.00
    的不同
    -2.00
     adolescente
    -1.99
    ar
    -1.96
    POSITIVE LOGITS
    <bos>
    2.95
    With
    2.73
    ,’
    2.53
    Not
    2.48
    fully
    2.47
    :”
    2.45
    …”
    2.45
    䊏
    2.41
    是
    2.41
     ikke
    2.39
    Activations Density 0.003%

    No Known Activations