© 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. 17911
    Prev
    Next
    INDEX
    Explanations

    words like Can, Buck, K, plastic

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

    romantic ambiance and realities

    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
    $&$
    0.42
     friend
    0.41
     Friend
    0.38
     Margarita
    0.38
     styr
    0.38
     situ
    0.38
    (|\
    0.37
     vind
    0.37
    [(\
    0.37
     footprint
    0.36
    POSITIVE LOGITS
    mrow
    0.42
    ylem
    0.41
     Wille
    0.39
     bicovariant
    0.39
     frameworks
    0.38
     formules
    0.38
    orphisms
    0.38
    ٹنگ
    0.38
    ERIC
    0.37
     formulae
    0.37
    Activations Density 0.000%

    No Known Activations