© 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. 34-GEMMASCOPE-RES-131K
    7. 108771
    Prev
    Next
    INDEX
    Explanations

    nowadays, today, these

    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_34/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
    bruck
    -1.00
    !==
    -0.99
    了不少
    -0.98
     previous
    -0.98
     belum
    -0.95
    ちゃんが
    -0.93
    autogui
    -0.92
    viamente
    -0.90
     lámpara
    -0.90
     hasta
    -0.89
    POSITIVE LOGITS
     nowadays
    6.59
     these
    5.00
    Nowadays
    4.75
     Nowadays
    4.69
    These
    3.42
     heut
    3.41
     today
    3.34
    这些
    3.27
    these
    3.25
     estos
    3.19
    Activations Density 0.273%

    No Known Activations