© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7337
    Prev
    Next
    INDEX
    Explanations

    ready when, crisis

    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_22_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
     জানুয়ার
    0.87
    똑
    0.85
    לה
    0.82
    脖
    0.81
    στό
    0.79
     aversion
    0.79
    Statistics
    0.78
     ende
    0.76
    ût
    0.76
     وسائل
    0.76
    POSITIVE LOGITS
    idin
    0.73
     thái
    0.73
     возраст
    0.67
    irin
    0.66
    iders
    0.66
    aghe
    0.65
     వచ్చిన
    0.64
    纵
    0.64
     الوز
    0.63
    叻
    0.63
    Activations Density 0.113%

    No Known Activations