© 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. 643
    Prev
    Next
    INDEX
    Explanations

    Google Android applications and services

    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
     McClellan
    1.09
     Empress
    1.03
     Morrissey
    0.99
     Bret
    0.96
     Peterborough
    0.95
     Dred
    0.93
    鴨
    0.93
    北大
    0.92
     Fife
    0.91
     Lich
    0.90
    POSITIVE LOGITS
     android
    1.87
     Android
    1.73
    android
    1.73
    Android
    1.70
     MainActivity
    1.66
     TextView
    1.58
     AppCompat
    1.57
    MainActivity
    1.54
     onCreate
    1.53
     EditText
    1.49
    Activations Density 0.281%

    No Known Activations