© 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. 7797
    Prev
    Next
    INDEX
    Explanations

    there is/are

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

    New Drug

    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
     Issued
    0.45
     issued
    0.40
    सायटी
    0.39
    하지
    0.38
    akiem
    0.38
    Œ
    0.38
    akke
    0.37
    istent
    0.36
    äng
    0.36
     ascribed
    0.36
    POSITIVE LOGITS
    句話
    0.43
     jam
    0.43
     traces
    0.43
     Roboto
    0.39
     diferencias
    0.39
     seguintes
    0.39
     Paragu
    0.39
    opis
    0.39
     韩
    0.38
     episod
    0.38
    Activations Density 0.010%

    No Known Activations