© 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. 68963
    Prev
    Next
    INDEX
    Explanations

    string interpolation in code

    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
     '
    -3.25
     You
    -3.00
     offizielle
    -2.64
     to
    -2.56
    人格
    -2.50
    、“
    -2.45
     
    -2.42
     If
    -2.38
    ist
    -2.33
    脆弱
    -2.22
    POSITIVE LOGITS
    埽
    3.28
    鋨
    2.84
    猻
    2.78
     identité
    2.59
    2.52
    缈
    2.47
    苳
    2.42
    씰
    2.41
    委员会
    2.39
    あっという間に
    2.38
    Activations Density 0.004%

    No Known Activations