© 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. 42035
    Prev
    Next
    INDEX
    Explanations

    1914

    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
    ون
    -1.63
    萏
    -1.27
    
    -1.27
    shid
    -1.25
     něco
    -1.24
    begin
    -1.24
     общения
    -1.24
    リ
    -1.24
     каждую
    -1.24
    ścic
    -1.23
    POSITIVE LOGITS
     their
    1.52
     from
    1.37
     about
    1.36
     against
    1.34
    1
    1.30
     vielfäl
    1.28
     esfuerzan
    1.24
     umfang
    1.20
     were
    1.19
    𝚕
    1.18
    Activations Density 0.022%

    No Known Activations