© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 805
    Prev
    Next
    INDEX
    Explanations

    by the + noun or gerund

    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
    </h1>
    -2.28
    </h3>
    -2.17
    л
    -1.88
    嘞
    -1.77
    cology
    -1.68
    },
    -1.65
     "..\..\..\
    -1.63
    (!__
    -1.60
    </th>
    -1.59
    actéristi
    -1.58
    POSITIVE LOGITS
     because
    1.83
    They
    1.74
     only
    1.58
    鯷
    1.57
    vailability
    1.49
     repeatedly
    1.48
     Endlich
    1.47
     since
    1.47
     although
    1.46
     what
    1.42
    Activations Density 0.007%

    No Known Activations