© 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. 8299
    Prev
    Next
    INDEX
    Explanations

    important to understand complexity

    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
     ug
    1.18
     fi
    1.15
     Superman
    1.08
     small
    1.07
     banana
    1.05
     _______
    1.05
     killed
    1.04
    だと思います
    1.03
     Banana
    1.03
     ____________
    1.02
    POSITIVE LOGITS
     populace
    1.72
     enthr
    1.71
     посредством
    1.67
    咱們
    1.65
    倘
    1.63
     endeavours
    1.63
     endeavors
    1.59
     sämt
    1.59
     elucid
    1.58
     countenance
    1.57
    Activations Density 0.906%

    No Known Activations