© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 4403
    Prev
    Next
    INDEX
    Explanations

    conditional conjunctions and code logic

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

    if/then conditional logic

    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
    ()},
    0.53
    .},
    0.51
    ]]).
    0.50
    '},
    0.48
     Затем
    0.46
    ')));
    0.46
    '))->
    0.45
    =?,
    0.44
    ())));
    0.44
    」、
    0.42
    POSITIVE LOGITS
     thì
    1.33
    则
    1.25
     فإن
    1.17
    則
    1.16
     Thì
    1.13
     maka
    1.12
     则
    1.09
    那么
    0.99
     তাহলে
    0.98
     allora
    0.97
    Activations Density 0.001%

    No Known Activations