© 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. 21588
    Prev
    Next
    INDEX
    Explanations

    beware or careful before

    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
     dança
    -1.47
    ımda
    -1.46
     spada
    -1.45
     soudain
    -1.45
    ſelves
    -1.41
     savez
    -1.41
    旁邊
    -1.40
     ノート
    -1.39
     célè
    -1.38
    
    -1.37
    POSITIVE LOGITS
     if
    2.11
     because
    1.92
     while
    1.87
     those
    1.84
     although
    1.81
     there
    1.77
     you
    1.77
     when
    1.75
     even
    1.66
     might
    1.51
    Activations Density 0.016%

    No Known Activations