© 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. 17510
    Prev
    Next
    INDEX
    Explanations

    predicting words that follow certain phrases

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

    slogans, syllabus, sperm, sclera, Sichuan

    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
    Sl
    0.62
    Su
    0.59
    Sa
    0.59
     Sl
    0.57
     Sa
    0.42
    SA
    0.41
    蘇
    0.41
    Si
    0.40
     Su
    0.40
    शाह
    0.39
    POSITIVE LOGITS
     Sutton
    2.05
    司
    2.05
    盛
    2.02
     scler
    1.95
     Sweeney
    1.90
     Snoop
    1.85
     SRAM
    1.84
     scl
    1.75
     للس
    1.73
     SDR
    1.71
    Activations Density 0.293%

    No Known Activations