© 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. 70713
    Prev
    Next
    INDEX
    Explanations

    data conversion and serialization

    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
     three
    -1.22
    🎶
    -1.08
     parcheggio
    -1.08
     after
    -1.05
     just
    -1.05
    meisters
    -1.04
     about
    -1.01
    髖
    -1.00
     guantes
    -0.99
     activity
    -0.97
    POSITIVE LOGITS
     Handles
    1.27
    pidou
    1.16
     défis
    1.15
    across
    1.13
    Handles
    1.10
    kében
    1.09
     difficultés
    1.08
    𝔱
    1.07
    вър
    1.06
    gasus
    1.06
    Activations Density 0.061%

    No Known Activations