© 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. 7-GEMMASCOPE-2-RES-16K
    7. 163
    Prev
    Next
    INDEX
    Explanations

    Sumo wrestling events

    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_7_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
     O
    1.39
    께
    1.32
    ga
    1.28
     to
    1.28
     அளவு
    1.27
    жный
    1.23
    ιος
    1.23
    YM
    1.23
     [
    1.20
    صیل
    1.20
    POSITIVE LOGITS
     PublicKey
    2.08
     legis
    1.99
    िक्ष
    1.96
    㕝
    1.94
    ธุรก
    1.93
    OMX
    1.90
     Appodeal
    1.89
     例文帳に追加
    1.89
    ँग्रेस
    1.84
    䞍
    1.83
    Activations Density 0.001%

    No Known Activations