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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10045
    Prev
    Next
    INDEX
    Explanations

    things that vary

    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
     supervise
    0.97
     vineyard
    0.91
     curative
    0.90
    itemView
    0.89
     supervising
    0.88
     нова
    0.88
    ilit
    0.87
    眄
    0.87
    栱
    0.86
     магистра
    0.85
    POSITIVE LOGITS
    fast
    1.14
     Fast
    1.02
     fast
    0.99
    Fast
    0.95
     fasted
    0.91
     REP
    0.91
     FAST
    0.89
     دنبال
    0.86
     rep
    0.85
    REP
    0.84
    Activations Density 0.209%

    No Known Activations