© 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. 119929
    Prev
    Next
    INDEX
    Explanations

    physical spaces

    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
    殽
    -2.36
    塒
    -2.03
     eſſ
    -1.77
    
    -1.73
    ༀ
    -1.71
     読む
    -1.70
    時から
    -1.60
    鲥
    -1.60
    lunda
    -1.59
    鸱
    -1.59
    POSITIVE LOGITS
    ).
    1.84
     how
    1.82
    ?
    1.81
     may
    1.73
    ٨
    1.64
    </u>
    1.61
     who
    1.60
    amarca
    1.59
    </th>
    1.59
     viagra
    1.59
    Activations Density 0.012%

    No Known Activations