© 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. 57547
    Prev
    Next
    INDEX
    Explanations

    US states and their politics

    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
     there
    -1.52
     lelaki
    -1.50
     Eropa
    -1.41
     Tahun
    -1.40
     kebakaran
    -1.39
    𝓰
    -1.38
     najdete
    -1.38
     eût
    -1.37
     Irán
    -1.36
    Often
    -1.34
    POSITIVE LOGITS
    </h5>
    1.54
    </b>
    1.42
     currently
    1.28
    聍
    1.25
    </u>
    1.25
     executive
    1.24
     direc
    1.20
     Ken
    1.20
     Imp
    1.18
     “
    1.17
    Activations Density 0.094%

    No Known Activations