© 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. 920
    Prev
    Next
    INDEX
    Explanations

    agreement and exclamations

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

    okay to start

    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
    𒄷
    0.33
     fortiter
    0.31
     نیز
    0.30
    )-,
    0.30
     userCollection
    0.30
     aberr
    0.29
     দায়ের
    0.29
     costitu
    0.29
     ಹಾಗೂ
    0.28
    詎
    0.28
    POSITIVE LOGITS
    hhh
    0.78
    !...
    0.75
     thats
    0.72
    !!!!
    0.68
    !..
    0.67
    hh
    0.64
    !!!
    0.64
    hhhh
    0.64
     yeah
    0.64
    !
    0.63
    Activations Density 0.334%

    No Known Activations