© 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. 9733
    Prev
    Next
    INDEX
    Explanations

    activation functions

    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
     vas
    0.94
     va
    0.91
     ‪
    0.88
    <0xEE>
    0.84
     complete
    0.82
    డవ
    0.81
    vot
    0.81
     ſ
    0.81
    éph
    0.81
     Vern
    0.80
    POSITIVE LOGITS
    td
    1.24
     Osiris
    1.12
    iful
    1.01
    꿈
    0.97
    either
    0.97
    স্বামী
    0.94
     Suh
    0.93
     Saif
    0.92
     الدفاع
    0.90
     السيد
    0.89
    Activations Density 0.004%

    No Known Activations