© 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. 73182
    Prev
    Next
    INDEX
    Explanations

    how something is compared

    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
     while
    -1.07
    当然是
    -0.97
     best
    -0.94
     pesar
    -0.92
     predomin
    -0.90
     notable
    -0.90
    ząd
    -0.89
    每個
    -0.88
    ladu
    -0.88
     welchen
    -0.87
    POSITIVE LOGITS
     compared
    1.10
    越南
    0.99
     biet
    0.98
     нынеш
    0.98
     ayaa
    0.93
     comparisons
    0.93
     comparison
    0.92
    metingen
    0.91
     how
    0.91
     comparación
    0.90
    Activations Density 0.037%

    No Known Activations