© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 63402
    Prev
    Next
    INDEX
    Explanations

    storage and retrieval

    np_acts-logits-general · gemini-2.5-flash-lite

    cost and payment avoidance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
                
    0.51
     n
    0.50
            
    0.48
    _{
    0.48
     While
    0.47
     WHAT
    0.47
    title
    0.47
               
    0.46
        
    0.46
    _
    0.46
    POSITIVE LOGITS
     almacen
    0.54
     almacenamiento
    0.53
     faciliter
    0.52
     empêcher
    0.51
     almacenar
    0.50
    是可以
    0.46
     karty
    0.46
     importe
    0.46
    储存
    0.46
     residencia
    0.45
    Activations Density 0.001%

    No Known Activations