© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48743
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
     deff
    -0.70
     adverti
    -0.69
     invul
    -0.67
    èn
    -0.65
     sensib
    -0.65
    JOBS
    -0.65
     poliuret
    -0.64
     Bochum
    -0.63
    isesta
    -0.63
     Stol
    -0.63
    POSITIVE LOGITS
     Trade
    0.74
     WY
    0.70
     plead
    0.69
    โซ
    0.69
     vys
    0.69
    siyah
    0.67
    raje
    0.67
     Army
    0.66
    στά
    0.66
    ське
    0.65
    Activations Density 0.137%

    No Known Activations