Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11966
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     karier
    -1.18
    lenme
    -1.17
     ความ
    -1.09
    芣
    -1.08
     ideen
    -1.05
    ům
    -1.02
     complacency
    -1.01
    惋
    -1.00
     travail
    -0.99
     familien
    -0.96
    POSITIVE LOGITS
    
    1.20
     thing
    1.19
     egli
    1.18
     можешь
    1.16
    𓄹
    1.13
     menurun
    1.13
     beschränkt
    1.11
     viewHolder
    1.11
     acá
    1.10
    _));
    1.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.