© 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. 34-GEMMASCOPE-RES-131K
    7. 102883
    Prev
    Next
    INDEX
    Explanations

    former POW, The Analysis

    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_34/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
    烩
    -0.85
     expressed
    -0.74
     έχει
    -0.70
     песня
    -0.70
    孩子们
    -0.69
     west
    -0.69
     Unterricht
    -0.68
     non
    -0.67
     after
    -0.67
    itinéraire
    -0.67
    POSITIVE LOGITS
    &&&
    0.92
    ULD
    0.91
     célè
    0.87
     dedo
    0.86
     alinea
    0.85
    дость
    0.85
     costes
    0.85
    </s>
    0.85
    bex
    0.84
    votre
    0.84
    Activations Density 0.021%

    No Known Activations