© 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. 4200
    Prev
    Next
    INDEX
    Explanations

    & symbol

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

    address-of operator `&`

    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
    Ꮸ
    0.37
     ͡
    0.36
    𝙙
    0.36
    راع
    0.34
    ],\
    0.34
    ٠
    0.33
    𠄌
    0.33
    牠
    0.33
    㚐
    0.33
    ('--
    0.32
    POSITIVE LOGITS
    &
    3.39
     &
    3.28
     &,
    2.69
     &.
    2.69
    ＆
    2.67
    &(
    2.66
    (&
    2.61
     &(
    2.61
    &\
    2.59
     (&
    2.59
    Activations Density 0.183%

    No Known Activations