© 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. 7581
    Prev
    Next
    INDEX
    Explanations

    car windows closed or cracked

    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
    ක්‍
    0.85
    Hamm
    0.84
     morning
    0.83
     <!
    0.83
    epid
    0.82
     Blunt
    0.82
     ক্র
    0.81
    IRD
    0.80
    ளு
    0.80
    ⚫
    0.80
    POSITIVE LOGITS
     넣어
    0.98
     ajudar
    0.97
     égal
    0.97
    പരി
    0.96
     forgotten
    0.94
     unheard
    0.93
     starve
    0.92
     memperbaiki
    0.92
     menikmati
    0.92
     unnoticed
    0.91
    Activations Density 0.000%

    No Known Activations