© 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. 7808
    Prev
    Next
    INDEX
    Explanations

    average followed by a metric

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

    average of

    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
     총
    0.42
    总
    0.40
    ัย
    0.39
     tổng
    0.39
     opportunities
    0.36
     بالح
    0.36
    的总
    0.36
     Allard
    0.35
    総
    0.35
     Ala
    0.35
    POSITIVE LOGITS
    পড়
    0.79
     joe
    0.76
    Joe
    0.74
     Joe
    0.69
    joe
    0.66
     арифмети
    0.64
    person
    0.61
    across
    0.57
    값을
    0.55
     age
    0.55
    Activations Density 0.034%

    No Known Activations