© 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. 7532
    Prev
    Next
    INDEX
    Explanations

    exception handling

    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
     biaya
    1.36
     عدة
    1.22
    際には
    1.22
    際は
    1.21
     dinyatakan
    1.20
    গামী
    1.19
    ")){
    1.19
    ाइंड
    1.18
     merupakan
    1.17
     berada
    1.16
    POSITIVE LOGITS
     පෙර
    1.18
     nó
    1.14
    -‘
    1.14
    其中
    1.10
     commonwealth
    1.08
    今
    1.08
    παν
    1.07
     it
    1.05
    arma
    1.00
     আমাদের
    1.00
    Activations Density 0.002%

    No Known Activations