© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38968
    Prev
    Next
    INDEX
    Explanations

    comparative phrases ending in than

    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
     モダン
    -0.98
     такими
    -0.93
     gustado
    -0.93
     BECOME
    -0.92
     somewhat
    -0.91
     comprennent
    -0.90
    completely
    -0.90
     такие
    -0.89
     setempat
    -0.88
     ALREADY
    -0.87
    POSITIVE LOGITS
     than
    2.69
     anywhere
    1.38
     any
    1.35
    than
    1.16
     anyone
    1.03
     those
    1.02
     nor
    1.02
     then
    1.02
     this
    1.02
     other
    0.97
    Activations Density 0.020%

    No Known Activations