© 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. 2856
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    parameter placeholders

    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
    aggers
    0.38
     gavel
    0.38
    伊
    0.35
    bmc
    0.34
     patriotism
    0.34
    apatillas
    0.34
    َاب
    0.33
    noff
    0.33
    长江
    0.33
     exh
    0.33
    POSITIVE LOGITS
     <!--
    0.42
     ",
    0.42
     _
    0.41
     _,
    0.40
     /*
    0.38
     _:
    0.38
     _{
    0.38
     "--
    0.36
     ()=>
    0.36
     ":
    0.36
    Activations Density 0.088%

    No Known Activations