© 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. 54251
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements

    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
     this
    -1.07
     sizable
    -0.97
    ácia
    -0.95
     bahawa
    -0.94
     considerable
    -0.94
     substantial
    -0.94
    visation
    -0.91
     people
    -0.90
    ॅ
    -0.90
    ifndef
    -0.85
    POSITIVE LOGITS
     they
    1.36
    他們
    1.31
     его
    1.31
     suoi
    1.20
     his
    1.13
     vaisseaux
    1.11
     Mereka
    1.08
     retours
    1.08
     its
    1.05
    TOGGLE
    1.05
    Activations Density 0.004%

    No Known Activations