© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 878
    Prev
    Next
    INDEX
    Explanations

    > and >>

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

    bolded list items

    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
     selfies
    0.48
     selfie
    0.46
     Selfie
    0.45
     (€
    0.43
     इंस्टाग्राम
    0.40
     ‍
    0.40
     catwalk
    0.38
    ℡
    0.38
    गिंग
    0.37
     YouTuber
    0.37
    POSITIVE LOGITS
     >
    0.76
    mailto
    0.76
     --
    0.75
    ...@
    0.75
    -----
    0.72
    >
    0.71
     -----
    0.70
    --------------
    0.69
    --
    0.68
     mailing
    0.68
    Activations Density 0.081%

    No Known Activations