© 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. 5023
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific terms

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

    computations and representations

    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
    骄
    0.48
    狹
    0.45
    क्के
    0.44
    顿
    0.43
     želite
    0.43
     серь
    0.42
    騷
    0.42
    鿷
    0.42
     dainty
    0.42
    बच्च
    0.42
    POSITIVE LOGITS
     satisfying
    0.91
     defined
    0.89
     describing
    0.86
     corresponding
    0.81
     constructed
    0.77
     parametrized
    0.76
    defined
    0.75
     indexed
    0.72
     whose
    0.71
     computed
    0.71
    Activations Density 0.026%

    No Known Activations