© 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. 7692
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis

    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
    leduj
    1.09
     tric
    1.09
    ikor
    1.07
    čna
    1.06
    晉
    1.06
    ikova
    1.05
    irinha
    1.04
    injector
    1.03
     সহজাত
    1.02
    ீர
    1.01
    POSITIVE LOGITS
    嵐
    0.76
     maturities
    0.76
    LX
    0.75
     commentaries
    0.72
     means
    0.72
    Lou
    0.71
     Atm
    0.70
    joe
    0.69
     فراهم
    0.68
     delay
    0.67
    Activations Density 0.018%

    No Known Activations