© 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. 63255
    Prev
    Next
    INDEX
    Explanations

    Microsoft development technologies

    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
     without
    -1.02
     ефек
    -0.95
    …！
    -0.93
    ってみる
    -0.88
    ！！
    -0.86
     when
    -0.86
     cheapest
    -0.85
     last
    -0.85
     with
    -0.84
     after
    -0.82
    POSITIVE LOGITS
    нки
    1.04
     ARISING
    1.03
     welches
    0.96
     ce
    0.96
     ms
    0.95
    ᷇
    0.95
    
    0.94
    螃
    0.93
    ܆
    0.91
    ms
    0.90
    Activations Density 0.016%

    No Known Activations