© 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. 48211
    Prev
    Next
    INDEX
    Explanations

    tailored and customized solutions

    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
    .
    -1.55
     in
    -1.46
     fables
    -1.35
    
    -1.28
     Significantly
    -1.25
     Essentially
    -1.25
     Incidentally
    -1.23
     voodoo
    -1.20
     It
    -1.20
     Angleterre
    -1.20
    POSITIVE LOGITS
     each
    1.55
     każdego
    1.50
     experiences
    1.48
    ፱
    1.46
    new
    1.45
     your
    1.39
     and
    1.39
     risposta
    1.38
    utivo
    1.37
     محف
    1.34
    Activations Density 0.040%

    No Known Activations