© 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. 1743
    Prev
    Next
    INDEX
    Explanations

    phone number and ID numbers

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

    number and quantity

    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
    gkin
    0.38
    万美元
    0.38
    জ্জামান
    0.37
    /∂
    0.36
    cznego
    0.34
    ពេញ
    0.34
    लट
    0.34
    湋
    0.34
    imethyl
    0.33
    捌章
    0.33
    POSITIVE LOGITS
     number
    4.56
    number
    4.25
     número
    3.89
     NUMBER
    3.80
     Number
    3.67
    Number
    3.64
    NUMBER
    3.64
     عدد
    3.64
     число
    3.53
     संख्या
    3.52
    Activations Density 0.435%

    No Known Activations