© 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. 5007
    Prev
    Next
    INDEX
    Explanations

    is it this

    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
     interchangeably
    0.92
     eller
    0.91
     or
    0.88
     oder
    0.81
    y
    0.81
    นะครับ
    0.81
     ou
    0.80
    または
    0.79
     หรือ
    0.76
     или
    0.75
    POSITIVE LOGITS
     Haziran
    1.47
    𐰣
    1.41
     voz
    1.40
     ![](
    1.40
     agosto
    1.38
     febrero
    1.36
    。【
    1.35
     enero
    1.35
     मद्देन
    1.34
    {[\
    1.33
    Activations Density 0.095%

    No Known Activations