© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109508
    Prev
    Next
    INDEX
    Explanations

    is/are followed by indefinite article or 'no'

    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
    UINTN
    -1.22
    כך
    -1.00
     augmenté
    -0.96
     gdy
    -0.94
     enfermos
    -0.93
     cirka
    -0.91
     menu
    -0.88
     milliers
    -0.88
    一周
    -0.88
     plateau
    -0.88
    POSITIVE LOGITS
     in
    1.73
     found
    1.39
     here
    1.32
     but
    1.19
     throughout
    1.17
     within
    1.11
     displayed
    1.09
     created
    1.09
     included
    1.05
     no
    1.05
    Activations Density 0.028%

    No Known Activations