© 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. 301
    Prev
    Next
    INDEX
    Explanations

    phone numbers

    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
     Bratislava
    0.80
     Ferenc
    0.79
     nội
    0.79
     viewDidLoad
    0.79
     VPT
    0.78
    瞠
    0.76
     jScrollPane
    0.75
    ີ
    0.75
    gry
    0.75
     Koš
    0.74
    POSITIVE LOGITS
    3
    1.10
    5
    1.07
    6
    1.06
    4
    1.01
    7
    1.01
    8
    0.98
    2
    0.95
    9
    0.94
    1
    0.88
     least
    0.68
    Activations Density 1.377%

    No Known Activations