© 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. 10265
    Prev
    Next
    INDEX
    Explanations

    account titles and debit/credit

    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
    ㇂
    2.61
    ẳn
    2.61
    десят
    2.57
    ્સ
    2.47
    ("|
    2.29
    snackbar
    2.28
    unctional
    2.25
    dent
    2.25
     Bás
    2.24
    ा
    2.24
    POSITIVE LOGITS
    ila
    1.99
    ous
    1.99
    after
    1.91
     dim
    1.89
    illa
    1.84
     Mok
    1.81
     occurrence
    1.80
    vis
    1.78
    ft
    1.77
     Succ
    1.77
    Activations Density 0.052%

    No Known Activations