© 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. 1299
    Prev
    Next
    INDEX
    Explanations

    information you can save

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

    actions and functions

    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
     artık
    0.46
     झाला
    0.45
     الاجتما
    0.43
    এ
    0.42
    自从
    0.42
     Agustus
    0.41
     الَّ
    0.41
     cinq
    0.41
     راستہ
    0.41
    是一种
    0.40
    POSITIVE LOGITS
    Nullable
    0.41
    😂
    0.40
    middot
    0.39
     פע
    0.39
    bauer
    0.37
    mDatas
    0.37
     عندي
    0.36
    youtube
    0.36
    Nguyen
    0.36
    и
    0.36
    Activations Density 0.389%

    No Known Activations