© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9439
    Prev
    Next
    INDEX
    Explanations

    to or would

    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
    read
    0.86
     अलविदा
    0.84
    ACK
    0.81
    許
    0.79
    充满了
    0.78
    uenza
    0.78
    ும
    0.78
    犾
    0.78
     receivable
    0.77
    itaj
    0.76
    POSITIVE LOGITS
     Vinci
    0.94
    ğın
    0.88
     Brat
    0.87
     pengh
    0.84
     বিন্দু
    0.81
     Mouth
    0.80
    мас
    0.78
    odils
    0.77
    ্শন
    0.77
     brat
    0.77
    Activations Density 0.073%

    No Known Activations