© 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. 10594
    Prev
    Next
    INDEX
    Explanations

    ultimately, crucially, consequently, importantly, frankly

    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
     BOTH
    1.09
     Both
    1.03
     neither
    1.03
     Anyway
    1.00
     Either
    0.96
     Neither
    0.96
    ?
    0.95
    ?:
    0.95
     huh
    0.95
     both
    0.92
    POSITIVE LOGITS
     consequently
    1.21
    などで
    1.18
     consequ
    1.13
     بنابراین
    1.12
     ditambah
    1.07
     consequent
    1.07
     др
    1.07
     dejado
    1.05
     později
    1.01
     subsequently
    1.00
    Activations Density 0.048%

    No Known Activations