© 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. 10-GEMMASCOPE-RES-131K
    4. 119480
    Prev
    Next
    INDEX
    Explanations

    own, another, any, every, to, enough

    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
     côtés
    -1.66
     Dinas
    -1.58
     revamped
    -1.54
     bienfaits
    -1.51
     verhind
    -1.47
     momentan
    -1.42
     acqua
    -1.41
     discer
    -1.40
     implor
    -1.40
     acco
    -1.38
    POSITIVE LOGITS
     so
    1.91
     this
    1.83
     there
    1.64
    there
    1.61
     information
    1.60
     even
    1.57
     plethora
    1.55
     noteworthy
    1.55
     at
    1.55
     used
    1.55
    Activations Density 0.099%

    No Known Activations