© 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. 90904
    Prev
    Next
    INDEX
    Explanations

    Most current

    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
    ￣)
    -0.84
    ???:
    -0.80
    Aus
    -0.78
    受信
    -0.78
    voyez
    -0.77
     musiciens
    -0.77
    ✨✨
    -0.77
    ❤️❤️❤️
    -0.75
     ressource
    -0.73
    ❤❤
    -0.71
    POSITIVE LOGITS
    smiles
    0.93
     móg
    0.82
    founded
    0.80
    q
    0.80
     añad
    0.80
    Tb
    0.78
    started
    0.77
     bijvoorbeeld
    0.76
    implies
    0.75
    kurse
    0.75
    Activations Density 0.019%

    No Known Activations