© 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. 793
    Prev
    Next
    INDEX
    Explanations

    temporal nouns and descriptions

    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
     کمی
    0.95
     somit
    0.93
     Somit
    0.91
    것
    0.90
     دارای
    0.89
     حسب
    0.89
     것이
    0.87
     जिनका
    0.87
    本次
    0.87
    렇
    0.87
    POSITIVE LOGITS
     researching
    2.09
     studying
    1.86
     navigating
    1.86
     doing
    1.82
     supervising
    1.79
     conducting
    1.78
     inspecting
    1.78
     preparing
    1.77
     trying
    1.77
     chasing
    1.75
    Activations Density 1.982%

    No Known Activations