© 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. 608
    Prev
    Next
    INDEX
    Explanations

    clothing and accessories

    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
     població
    0.80
    layout
    0.80
    析
    0.79
     بیک
    0.78
    LocalDateTime
    0.78
    adec
    0.77
     indetermin
    0.76
    htë
    0.74
    瀧
    0.74
    出荷
    0.73
    POSITIVE LOGITS
     gloves
    2.15
     sunglasses
    1.96
     goggles
    1.94
     helmet
    1.89
     Gloves
    1.82
     raincoat
    1.81
     headphones
    1.81
     mittens
    1.78
     helmets
    1.78
     Sunglasses
    1.69
    Activations Density 3.444%

    No Known Activations