© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5877
    Prev
    Next
    INDEX
    Explanations

    Cuddle, DC, photo, Doki, Copper, Obsolete, Analysis, cp

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

    punctuated phrases

    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
     Ā
    0.46
     !,
    0.46
     "-",
    0.44
     $(-
    0.44
     (?,
    0.43
     …,
    0.43
     (\<
    0.43
     („
    0.42
     +,
    0.42
    #,
    0.42
    POSITIVE LOGITS
    ՝
    0.59
    ¨
    0.59
    丶
    0.52
    ``
    0.51
    ‚
    0.50
    `
    0.48
    ˋ
    0.48
    
    0.47
    ›
    0.47
    ㆍ
    0.46
    Activations Density 0.277%

    No Known Activations