© 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. 69412
    Prev
    Next
    INDEX
    Explanations

    best way to

    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
    -
    -1.66
    ,
    -1.38
     “
    -1.37
     hecha
    -1.32
     one
    -1.24
     cuadrada
    -1.20
     reconocida
    -1.20
     wykonane
    -1.20
     almohada
    -1.18
    hias
    -1.17
    POSITIVE LOGITS
     to
    1.77
    </td>
    1.63
     maniere
    1.59
    ijão
    1.49
    тории
    1.48
     for
    1.46
     estadounid
    1.44
     内衣
    1.40
     prata
    1.39
     ways
    1.37
    Activations Density 0.067%

    No Known Activations