© 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. 10-GEMMASCOPE-RES-131K
    7. 130775
    Prev
    Next
    INDEX
    Explanations

    make, made, making, doing, written, given

    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_10/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
    man
    -2.22
    ]
    -2.20
    璈
    -2.13
    s
    -2.11
    m
    -2.08
    able
    -2.06
    鶿
    -2.05
    also
    -2.03
     discussions
    -1.95
     movimenti
    -1.95
    POSITIVE LOGITS
    '
    2.81
     machen
    2.27
    1
    2.22
    綃
    2.16
    Mostly
    2.11
     fashioned
    2.08
     Frequently
    2.03
     Mostly
    2.02
    
    1.96
     rampant
    1.94
    Activations Density 0.001%

    No Known Activations