© 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. 1518
    Prev
    Next
    INDEX
    Explanations

    augments or augments

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

    ought aug Forced

    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
     chicas
    0.45
     sociais
    0.44
     Sociales
    0.43
    Shannon
    0.41
    printf
    0.40
    bibli
    0.39
    ㄣ
    0.39
    atif
    0.39
    ῳ
    0.38
    જ
    0.38
    POSITIVE LOGITS
     aug
    0.79
    ought
    0.69
     ought
    0.68
     augment
    0.63
     Aug
    0.62
    Aug
    0.61
    aught
    0.60
    aug
    0.60
     augmentation
    0.58
     forced
    0.57
    Activations Density 0.000%

    No Known Activations