© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9510
    Prev
    Next
    INDEX
    Explanations

    day or way phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     prized
    1.66
    ν
    1.57
     regarded
    1.56
    慓
    1.52
    シール
    1.52
    blkid
    1.52
    સ્
    1.50
    ನಾಡ
    1.50
     vigorous
    1.48
    最高の
    1.48
    POSITIVE LOGITS
     Tang
    1.05
     x
    1.03
     tab
    1.03
     problemen
    0.99
    ogn
    0.99
     papi
    0.97
     Fol
    0.96
    ณิต
    0.94
     jong
    0.93
     pog
    0.93
    Activations Density 0.070%

    No Known Activations