© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17132
    Prev
    Next
    INDEX
    Explanations

    location or property

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

    compromise operations, you need

    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
     አካ
    0.43
    erd
    0.43
     rounded
    0.42
    achi
    0.41
     pays
    0.39
    "]),
    0.39
    "},
    0.39
    ","",
    0.38
    "],"
    0.37
    "]},
    0.37
    POSITIVE LOGITS
    divided
    0.46
     Divided
    0.46
     discounting
    0.46
    折扣
    0.43
    సక్తి
    0.41
     divided
    0.41
    स्वागत
    0.40
    ዐ
    0.39
     tratado
    0.39
    があれば
    0.38
    Activations Density 0.000%

    No Known Activations