© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11920
    Prev
    Next
    INDEX
    Explanations

    presenting options and choices

    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
     国家
    1.24
    த்தகைய
    1.15
    χο
    1.14
     あの
    1.13
    州
    1.06
     Aquarelle
    1.06
    χη
    1.05
    ಂತಹ
    1.04
    州的
    1.04
     সার্বভৌম
    1.04
    POSITIVE LOGITS
     резко
    0.87
    กัน
    0.81
    กด
    0.79
    эд
    0.79
     gummies
    0.79
     собра
    0.74
    删
    0.72
    แปล
    0.72
     fork
    0.71
     பா
    0.70
    Activations Density 0.020%

    No Known Activations