© 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. 72920
    Prev
    Next
    INDEX
    Explanations

    unmet needwellposedness, problematic

    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
    </td>
    -2.80
    </h5>
    -2.44
     ""
    -2.16
     principais
    -2.06
     \\
    -2.05
     preocu
    -2.03
     десять
    -2.02
    给予
    -1.95
     молока
    -1.94
     pleaſure
    -1.93
    POSITIVE LOGITS
    </strong>
    2.98
    '
    2.78
    *
    2.45
     moot
    2.22
    \
    2.16
    ,”
    2.14
     italia
    2.03
    ness
    1.95
     milano
    1.91
     желание
    1.91
    Activations Density 0.001%

    No Known Activations