© 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. 10-GEMMASCOPE-RES-131K
    7. 71803
    Prev
    Next
    INDEX
    Explanations

    interventional measures

    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
     tireless
    -2.56
    ㆆ
    -2.50
     reorgan
    -2.39
    та
    -2.33
     resurrect
    -2.28
     ‘
    -2.22
      
    -2.02
    ن
    -1.98
     minim
    -1.97
     wrecking
    -1.95
    POSITIVE LOGITS
    {
    3.16
    那里
    2.47
     pusieron
    2.36
    窳
    2.31
    蟊
    2.30
    ৄ
    2.30
    ႐
    2.14
     装着
    2.09
    粢
    2.09
     ofreci
    2.08
    Activations Density 0.000%

    No Known Activations