© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2400
    Prev
    Next
    INDEX
    Explanations

    use start apply

    np_acts-logits-general · gemini-2.5-flash-lite

    installing and setting up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_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
     hinted
    0.40
    খ্যার
    0.40
    烣
    0.39
    ქვ
    0.37
     друга
    0.35
    casian
    0.35
    רה
    0.35
    doctoral
    0.35
     ذر
    0.34
     unlikely
    0.34
    POSITIVE LOGITS
     Ping
    0.61
     Start
    0.51
     Apply
    0.51
     О
    0.50
     ホーム
    0.49
     Soccer
    0.49
     Опреде
    0.49
    Ping
    0.48
     ping
    0.48
     С
    0.47
    Activations Density 0.016%

    No Known Activations