© 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. 59564
    Prev
    Next
    INDEX
    Explanations

    as a way to

    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
    　↓
    -1.89
     there
    -1.80
    評價
    -1.78
    When
    -1.77
    文獻
    -1.73
    ಞ
    -1.70
    記錄
    -1.66
    當中
    -1.66
    類型
    -1.66
    Ruju
    -1.64
    POSITIVE LOGITS
    ኗ
    1.86
     sendo
    1.81
     echte
    1.78
     of
    1.76
     anderen
    1.73
     “
    1.72
     другими
    1.70
     étant
    1.68
     normalen
    1.66
     zumal
    1.64
    Activations Density 0.005%

    No Known Activations