© 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. 103832
    Prev
    Next
    INDEX
    Explanations

    commercial use

    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
    raim
    -0.83
    登場
    -0.80
    urige
    -0.79
    を担当
    -0.77
    Ecc
    -0.75
    רוב
    -0.75
     좋아
    -0.75
    zubauen
    -0.74
     BIBLIO
    -0.74
     ノート
    -0.74
    POSITIVE LOGITS
     commercial
    2.94
    commercial
    2.69
    Commercial
    2.44
     Commercial
    2.23
     comercial
    2.05
     COMMERCIAL
    2.05
    COMMERCIAL
    1.97
     коммер
    1.89
     commerciale
    1.80
     commercially
    1.80
    Activations Density 0.081%

    No Known Activations