© 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. 17251
    Prev
    Next
    INDEX
    Explanations

    highway number

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

    numbers and codes

    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
     சுமார்
    0.48
    approximately
    0.48
     noin
    0.47
     साढ़े
    0.45
     approximately
    0.44
    (`${
    0.43
     stoichi
    0.42
    ⸱
    0.41
    唃
    0.40
     اربع
    0.40
    POSITIVE LOGITS
    אי
    0.40
    מס
    0.40
     क्रमांक
    0.39
    прочем
    0.39
     Nº
    0.38
     accuracies
    0.38
    лин
    0.37
    рус
    0.37
    лера
    0.36
    来た
    0.36
    Activations Density 0.068%

    No Known Activations