© 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. 26010
    Prev
    Next
    INDEX
    Explanations

    closing code blocks

    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
     Grüße
    -0.97
     søndag
    -0.96
     (
    -0.95
     lørdag
    -0.91
    idable
    -0.90
     to
    -0.89
     will
    -0.88
    đầm
    -0.87
    //'
    -0.85
    𒊹
    -0.84
    POSITIVE LOGITS
     tendencias
    1.08
     erweitert
    1.02
    ริม
    1.02
     verhindern
    0.98
     produto
    0.96
     função
    0.94
    </h4>
    0.91
    たびに
    0.91
     maneira
    0.90
     conversaciones
    0.90
    Activations Density 0.007%

    No Known Activations