© 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. 22-GEMMASCOPE-RES-131K
    4. 93236
    Prev
    Next
    INDEX
    Explanations

    External links and categories

    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
     kabar
    -1.17
     turista
    -1.15
     esposo
    -1.06
     pouvons
    -1.06
    Ꮚ
    -1.04
     parachoque
    -1.02
    蕺
    -1.02
    
    -1.01
     sprüche
    -1.01
     ١
    -1.01
    POSITIVE LOGITS
     two
    0.98
    gin
    0.96
     Kriege
    0.92
    two
    0.92
     by
    0.91
     firebaseConfig
    0.86
     due
    0.85
    amon
    0.84
     time
    0.84
    sup
    0.84
    Activations Density 0.001%

    No Known Activations