© 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. 34-GEMMASCOPE-RES-131K
    7. 395
    Prev
    Next
    INDEX
    Explanations

    dividing or separating

    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_34/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
    ombic
    -0.81
     Burrow
    -0.79
    lateur
    -0.78
    <![
    -0.77
    Persona
    -0.75
    Ⓔ
    -0.74
     Warne
    -0.74
    Navbar
    -0.74
    번호
    -0.73
    Aspect
    -0.73
    POSITIVE LOGITS
     separating
    3.97
     separates
    3.11
     dividing
    3.09
     divides
    2.86
     separation
    2.75
     divide
    2.61
     separator
    2.36
    separ
    2.34
     Separ
    2.28
     separations
    2.27
    Activations Density 0.107%

    No Known Activations