© 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. 2046
    Prev
    Next
    INDEX
    Explanations

    list item prefixes and content

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

    mathematical expressions and sets

    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
    ᖕ
    0.62
    HasStarred
    0.60
     territo
    0.59
    影响力
    0.55
     railings
    0.53
    ༠
    0.52
     stoves
    0.51
     fuelwood
    0.51
    代表人
    0.50
    <unused47>
    0.49
    POSITIVE LOGITS
     ta
    0.89
     Ta
    0.84
     Xét
    0.84
    Gọi
    0.83
    =>
    0.82
    Ta
    0.81
    ta
    0.78
    Vậy
    0.77
     =>
    0.75
    Xét
    0.75
    Activations Density 0.001%

    No Known Activations