© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 5031
    Prev
    Next
    INDEX
    Explanations

    paying attention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    csdn
    1.80
     reprogram
    1.69
     fetchData
    1.57
    ransform
    1.56
    uzten
    1.54
    CRIPT
    1.52
     Ignite
    1.49
     /\.
    1.47
    attham
    1.47
    enched
    1.46
    POSITIVE LOGITS
     consideration
    2.30
     attention
    2.18
     importance
    2.06
    attention
    2.05
     attenzione
    1.96
    importance
    1.95
     Attention
    1.92
    attenzione
    1.90
     utmost
    1.89
     concern
    1.86
    Activations Density 0.196%

    No Known Activations