© 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. 7504
    Prev
    Next
    INDEX
    Explanations

    numerical ranges

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

    rating scales from low

    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
     PERCENT
    0.45
     Mas
    0.44
     CALCUL
    0.44
    OHN
    0.42
     porcent
    0.39
    鎿
    0.38
     Calcul
    0.38
     percent
    0.38
     процентов
    0.38
     Pep
    0.37
    POSITIVE LOGITS
    щению
    0.43
     digitized
    0.43
     alphabetically
    0.42
    ப்பதை
    0.41
    🚭
    0.40
     যাওয়ার
    0.40
     scrutinized
    0.40
     montañas
    0.39
     incidentally
    0.39
    รายละเอียด
    0.39
    Activations Density 0.001%

    No Known Activations