© 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. 7131
    Prev
    Next
    INDEX
    Explanations

    US resources

    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
     အမျိုး
    0.88
    碾
    0.86
     UID
    0.86
     جیت
    0.86
    ioon
    0.86
    uko
    0.85
     पैटर्न
    0.85
     microcontroller
    0.84
     UFC
    0.84
     جیتنے
    0.84
    POSITIVE LOGITS
     leprosy
    1.25
    laz
    1.12
     lepro
    1.11
    Lep
    1.07
     tubercle
    1.06
    痳
    1.05
     Plague
    1.05
     tubercles
    1.03
    pox
    1.01
    痨
    1.01
    Activations Density 0.108%

    No Known Activations