© 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. 10252
    Prev
    Next
    INDEX
    Explanations

    fear of missing out

    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
    থেষ্ট
    2.41
    údio
    2.37
    éor
    2.30
    epic
    2.30
    扆
    2.27
    ющее
    2.25
    তায়
    2.21
     inglese
    2.20
     สวัสดี
    2.19
    تك
    2.19
    POSITIVE LOGITS
     voc
    2.03
     Bonding
    2.02
     bonding
    1.86
     withheld
    1.83
    꽁
    1.81
    den
    1.80
     omission
    1.78
    сь
    1.75
    ilipp
    1.73
    bate
    1.71
    Activations Density 0.001%

    No Known Activations