© 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. 13-GEMMASCOPE-2-RES-65K
    7. 2340
    Prev
    Next
    INDEX
    Explanations

    don't / doesn't / haven't

    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_13_width_65k_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
    𐰲
    1.93
     gstlal
    1.90
     BSData
    1.89
    𐰢
    1.88
    𐰀
    1.87
    𐰑
    1.87
     ہُما
    1.87
    𒊺
    1.87
    𒀫
    1.87
    𐰖
    1.85
    POSITIVE LOGITS
     and
    1.19
     South
    1.19
     Southern
    1.13
    ’
    1.11
     “
    1.10
     southern
    1.09
     national
    1.04
     Christian
    1.03
     ‘
    1.03
     National
    1.00
    Activations Density 0.628%

    No Known Activations