© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 7392
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    iambic pentameter

    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
     proactively
    0.56
     મહિલા
    0.53
     iteratively
    0.53
    ិនបើ
    0.52
    Ⲣ
    0.50
     comorbid
    0.50
     demographics
    0.50
     tagline
    0.50
     ситуа
    0.50
     టీడీపీ
    0.50
    POSITIVE LOGITS
    ⁠
    0.60
    ,—
    0.53
     scarcely
    0.52
    ​—
    0.52
    ȧ
    0.49
    CHAPTER
    0.48
     men
    0.48
     Lieut
    0.47
     chiefly
    0.45
    ment
    0.45
    Activations Density 0.045%

    No Known Activations