© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 95723
    Prev
    Next
    INDEX
    Explanations

    contrasting choices

    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
    -0.96
     directly
    -0.81
     Citron
    -0.81
    fiche
    -0.81
     paragraphe
    -0.79
     médecin
    -0.78
    HAHAHA
    -0.76
     CountDown
    -0.76
     Reprint
    -0.75
    illets
    -0.74
    POSITIVE LOGITS
     prefer
    1.29
     preferred
    1.24
     if
    1.19
     optional
    1.13
    optional
    1.11
    preferred
    1.10
     preferable
    1.05
     Prefer
    1.03
     بهتر
    1.02
     nicer
    1.00
    Activations Density 0.043%

    No Known Activations