© 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. 22-GEMMASCOPE-RES-131K
    7. 65444
    Prev
    Next
    INDEX
    Explanations

    names and code structure

    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_22/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
     وزير
    -0.97
    ridescent
    -0.93
    moji
    -0.92
    both
    -0.91
     både
    -0.90
    aried
    -0.88
     yere
    -0.88
     lamentable
    -0.87
    entification
    -0.86
     kedua
    -0.85
    POSITIVE LOGITS
     by
    1.04
    Ucraina
    0.90
     started
    0.88
     hư
    0.88
     one
    0.87
     включа
    0.85
     particularly
    0.85
     convencer
    0.85
     could
    0.84
     cucchiai
    0.83
    Activations Density 0.001%

    No Known Activations