© 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. 119398
    Prev
    Next
    INDEX
    Explanations

    grammatical objects or counts

    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
     about
    -1.51
     priva
    -1.50
     Ansatz
    -1.47
     now
    -1.46
     commerci
    -1.44
     comprising
    -1.41
    elerik
    -1.32
     such
    -1.31
     termed
    -1.28
     conto
    -1.26
    POSITIVE LOGITS
     enemigo
    1.38
     ilustração
    1.36
     estadia
    1.30
     seção
    1.30
     frail
    1.30
     גם
    1.29
     gustan
    1.28
    柘
    1.28
     manuell
    1.28
     negocia
    1.27
    Activations Density 0.015%

    No Known Activations