© 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. 1046
    Prev
    Next
    INDEX
    Explanations

    as I / as a

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

    as well

    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
     ambayo
    0.30
     whiche
    0.26
     상당
    0.26
    =(
    0.26
    荘
    0.25
     consigui
    0.25
    them
    0.25
    )+
    0.25
    ซึ่ง
    0.25
     Which
    0.24
    POSITIVE LOGITS
     opposed
    1.01
    sembles
    0.79
    ymmet
    0.76
     soon
    0.75
     oppose
    0.72
    cribing
    0.72
     evidenced
    0.71
    cribable
    0.67
     well
    0.66
     far
    0.64
    Activations Density 0.420%

    No Known Activations