© 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. 10448
    Prev
    Next
    INDEX
    Explanations

    minimizes direct manipulation

    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
    ̊
    0.97
    ⺠
    0.88
    全民
    0.88
    ̆
    0.88
     지나
    0.86
     수상
    0.86
     COVID
    0.85
     offent
    0.85
    aths
    0.84
    omes
    0.84
    POSITIVE LOGITS
    Brightness
    1.03
    Rabbit
    1.01
    heben
    1.00
    Warranty
    0.99
    gambar
    0.97
     refrigerators
    0.96
    Cat
    0.95
    -__
    0.94
    hebung
    0.94
     washers
    0.94
    Activations Density 0.005%

    No Known Activations