© 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. 92097
    Prev
    Next
    INDEX
    Explanations

    html, css, meta tags

    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
    ņem
    -0.69
    ntos
    -0.66
     nước
    -0.64
     recruitment
    -0.64
     Orphan
    -0.62
    ETTA
    -0.62
    生命
    -0.62
     ग्राहक
    -0.61
    clr
    -0.61
    bbb
    -0.60
    POSITIVE LOGITS
    
    0.73
    鏽
    0.71
    寄生
    0.68
    THING
    0.66
     Term
    0.66
     acum
    0.66
    сни
    0.66
    Std
    0.66
    ouds
    0.65
     essentiels
    0.65
    Activations Density 0.080%

    No Known Activations