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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5890
    Prev
    Next
    INDEX
    Explanations

    for loops in code

    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
     mengatakan
    1.44
     afferma
    1.38
    ंदरे
    1.36
     afirmó
    1.28
    ፓ
    1.22
     stwier
    1.21
    Những
    1.20
     menjelaskan
    1.19
    arının
    1.19
     মহাশয়ের
    1.18
    POSITIVE LOGITS
     source
    0.72
    .…
    0.66
    …
    0.65
     respect
    0.61
     fres
    0.59
    source
    0.58
     J
    0.57
    ny
    0.56
    реза
    0.55
     all
    0.54
    Activations Density 0.034%

    No Known Activations