© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10183
    Prev
    Next
    INDEX
    Explanations

    mon amour

    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_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ỡi
    2.89
    failures
    2.76
     הער
    2.71
     failures
    2.66
    Fail
    2.63
    स्‍ट
    2.62
    filenames
    2.61
    itching
    2.59
     चेयरमैन
    2.58
    礙
    2.57
    POSITIVE LOGITS
    er
    2.70
    ر
    2.64
    ogical
    2.52
    तः
    2.34
    ogy
    2.28
    erende
    2.28
    erol
    2.28
    ution
    2.24
     ذره
    2.21
    utely
    2.20
    Activations Density 0.004%

    No Known Activations