© 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. 8472
    Prev
    Next
    INDEX
    Explanations

    words or fragments in various scripts

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

    Hugging Face models

    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
     lottery
    0.51
     Lottery
    0.46
     raffle
    0.45
     ₹
    0.42
    utte
    0.42
     dreamer
    0.41
     Lotto
    0.40
    metto
    0.40
    lot
    0.40
     लॉ
    0.39
    POSITIVE LOGITS
    )/\
    0.39
     MATTER
    0.38
    編成
    0.36
    Transactional
    0.35
     inhaled
    0.34
    /***
    0.34
    КИ
    0.33
     γνωσ
    0.33
    巨人
    0.33
     KIND
    0.33
    Activations Density 0.000%

    No Known Activations