© 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. 70579
    Prev
    Next
    INDEX
    Explanations

    process or state completion

    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
     Cancelar
    -1.38
     internes
    -1.38
    sekten
    -1.34
     varier
    -1.34
    купить
    -1.32
     Ministre
    -1.28
     malen
    -1.28
     personnalisées
    -1.27
     berge
    -1.27
    这些
    -1.27
    POSITIVE LOGITS
     you
    1.63
     it
    1.53
     available
    1.45
    그러나
    1.35
     remaining
    1.35
     north
    1.32
    杌
    1.30
     Germany
    1.30
     time
    1.27
     offering
    1.27
    Activations Density 0.119%

    No Known Activations