© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73136
    Prev
    Next
    INDEX
    Explanations

    archaic or clipped words

    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
    </h2>
    -2.53
     Saltar
    -1.75
     caiu
    -1.53
     schmerz
    -1.50
    
    -1.48
     estudo
    -1.48
     byly
    -1.48
     convite
    -1.44
    姈
    -1.43
     suspected
    -1.38
    POSITIVE LOGITS
     or
    1.75
    at
    1.70
     thema
    1.54
    ↵
    1.53
     when
    1.48
     keduanya
    1.46
     eet
    1.46
     because
    1.43
     oras
    1.40
    мам
    1.38
    Activations Density 0.024%

    No Known Activations