© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13406
    Prev
    Next
    INDEX
    Explanations

    error logging and printing

    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
     synopsis
    1.32
     succinct
    1.26
    𝐼
    1.24
     summarize
    1.23
    summar
    1.20
     prudent
    1.20
     summarise
    1.19
    initial
    1.17
    𝑍
    1.15
     indol
    1.14
    POSITIVE LOGITS
     অথবা
    1.29
     والط
    1.17
     restric
    1.16
     Restrictions
    1.16
     residente
    1.14
    และความ
    1.14
    家人
    1.13
    หรือ
    1.13
     autó
    1.11
    又は
    1.10
    Activations Density 0.105%

    No Known Activations