© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 13944
    Prev
    Next
    INDEX
    Explanations

    unique descriptor followed by noun

    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
     vegano
    -1.90
     you
    -1.90
    艄
    -1.87
     gela
    -1.71
     rangi
    -1.68
     tirs
    -1.65
    
    -1.65
     manto
    -1.64
     noten
    -1.64
     stap
    -1.59
    POSITIVE LOGITS
     own
    2.38
    </h2>
    2.28
     and
    2.22
     And
    1.60
     at
    1.56
     or
    1.56
    ları
    1.55
     With
    1.52
     d
    1.49
    </h3>
    1.46
    Activations Density 0.012%

    No Known Activations