© 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. 7139
    Prev
    Next
    INDEX
    Explanations

    home

    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
    untz
    0.94
    ափ
    0.93
    铱
    0.92
    油脂
    0.88
    ✫
    0.88
     sdf
    0.87
    antemente
    0.86
     zirconium
    0.85
    zIndex
    0.85
    锑
    0.85
    POSITIVE LOGITS
     home
    4.54
    home
    4.28
     house
    4.12
     homes
    4.09
    Home
    4.04
     Home
    4.00
     HOME
    3.90
     casa
    3.85
    HOME
    3.74
    homes
    3.70
    Activations Density 0.895%

    No Known Activations