© 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. 10-GEMMASCOPE-RES-131K
    4. 20474
    Prev
    Next
    INDEX
    Explanations

    even with

    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
     is
    -2.38
    </td>
    -1.98
    </h4>
    -1.92
    </h5>
    -1.91
     has
    -1.83
     like
    -1.74
     by
    -1.71
    o
    -1.66
    </b>
    -1.63
     was
    -1.59
    POSITIVE LOGITS
     bús
    1.74
     llegamos
    1.62
     pedimos
    1.61
    licitud
    1.52
     quieras
    1.50
     rése
    1.50
     estés
    1.49
     seleccionamos
    1.48
     funcione
    1.48
     bēr
    1.47
    Activations Density 0.004%

    No Known Activations