© 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. 34-GEMMASCOPE-RES-131K
    4. 45673
    Prev
    Next
    INDEX
    Explanations

    public class or method declarations

    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
    чева
    -0.96
     at
    -0.89
     equipa
    -0.87
    zają
    -0.87
     AudioClip
    -0.85
     Menggunakan
    -0.84
     imobili
    -0.82
    IVENESS
    -0.81
     bondage
    -0.81
     {};
    -0.80
    POSITIVE LOGITS
    public
    1.26
     bool
    1.23
     async
    1.02
    ($"{
    0.99
     virtual
    0.98
     public
    0.95
    ($"
    0.88
    arkiv
    0.87
    ">
    
    0.87
    bool
    0.87
    Activations Density 0.012%

    No Known Activations