© 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. 5030
    Prev
    Next
    INDEX
    Explanations

    actions followed by details

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

    gerunds ending in -ing

    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
    heading
    0.41
    鋲
    0.40
     recognise
    0.38
     Sarkar
    0.38
    iophorus
    0.38
    chosen
    0.38
     Mena
    0.37
     choked
    0.37
     recognize
    0.37
    בע
    0.37
    POSITIVE LOGITS
     ബന്ധ
    0.41
     zv
    0.41
     dziecka
    0.41
     fistule
    0.40
     தன்மை
    0.40
    郑
    0.40
    HeaderAccept
    0.39
     ucz
    0.39
    垍
    0.38
     abruptly
    0.38
    Activations Density 0.000%

    No Known Activations