© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130299
    Prev
    Next
    INDEX
    Explanations

    occupation, address, database, RANK, true

    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
     rád
    -1.09
     禮
    -0.94
     septembre
    -0.93
     ANZ
    -0.93
     septiembre
    -0.91
    مال
    -0.89
    ״
    -0.88
     їх
    -0.87
    entiary
    -0.87
    itarios
    -0.87
    POSITIVE LOGITS
     wesentlichen
    0.99
    使って
    0.86
     corpi
    0.85
     التد
    0.80
     wichtige
    0.79
     whether
    0.79
     following
    0.79
     veränder
    0.78
     rebuilding
    0.77
     bestehenden
    0.77
    Activations Density 0.152%

    No Known Activations