© 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. 110512
    Prev
    Next
    INDEX
    Explanations

    by-product or election

    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
    ка
    -2.31
    of
    -2.28
    </i>
    -2.27
    ?
    -2.25
     gradual
    -2.11
    \
    -2.09
    </h1>
    -2.09
     has
    -1.98
     или
    -1.95
    憮
    -1.94
    POSITIVE LOGITS
    囖
    2.72
    
    2.53
    尨
    2.44
     素描
    2.19
    𐐀
    2.17
    鹟
    2.14
    llavero
    2.11
     Consejos
    2.11
     Derechos
    2.11
     verhind
    2.11
    Activations Density 0.015%

    No Known Activations