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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 2026
    Prev
    Next
    INDEX
    Explanations

    readability and understandability 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
    a
    1.85
    o
    1.68
    ി
    1.63
    на
    1.49
    aar
    1.48
    دول
    1.47
    نما
    1.46
    onomy
    1.44
    ്
    1.44
    lovl
    1.41
    POSITIVE LOGITS
    ErrorKind
    1.97
     Türkçe
    1.93
     trattano
    1.92
     Έ
    1.92
    BibitemOpen
    1.88
     ROSE
    1.86
     fallo
    1.85
     หนู
    1.82
     Συ
    1.81
     coseno
    1.80
    Activations Density 0.003%

    No Known Activations