© 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. 10014
    Prev
    Next
    INDEX
    Explanations

    Power BI, business intelligence

    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
     endowment
    0.97
    g
    0.84
     endowments
    0.83
     cork
    0.83
     መጠ
    0.81
     softwood
    0.81
    plicative
    0.81
     rappel
    0.79
    ternut
    0.79
     graces
    0.77
    POSITIVE LOGITS
    ān
    1.17
    пси
    0.99
    anes
    0.99
    𝐚
    0.97
    JK
    0.96
    blob
    0.96
    rmse
    0.95
    𝐫
    0.93
    боро
    0.93
    ams
    0.91
    Activations Density 0.015%

    No Known Activations