© 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. 130993
    Prev
    Next
    INDEX
    Explanations

    React component syntax

    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
     klima
    -1.08
     jule
    -1.07
     setDescription
    -0.94
    ⊿
    -0.93
     loadImage
    -0.92
     teolog
    -0.91
     Эти
    -0.90
     merito
    -0.90
     ortop
    -0.90
    斗
    -0.90
    POSITIVE LOGITS
     estatales
    1.27
     sanitarias
    1.16
    象徴
    1.13
     dlaczego
    1.04
     možnost
    1.03
    エスト
    1.03
     React
    1.02
    ないし
    1.02
     interesados
    1.01
     législation
    1.01
    Activations Density 0.005%

    No Known Activations