© 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. 4174
    Prev
    Next
    INDEX
    Explanations

    athlete names

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

    First name last name pairs

    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
     बीसीसीआई
    0.55
     PlayerSelector
    0.53
     Баскетбол
    0.52
    ⟋
    0.51
    犃
    0.50
    㫻
    0.50
    夆
    0.50
     क्रिकेट
    0.50
     باشگاه
    0.50
    嬂
    0.50
    POSITIVE LOGITS
    att
    0.56
    if
    0.55
    o
    0.55
    as
    0.52
    ar
    0.52
    ier
    0.52
    br
    0.51
    on
    0.50
    re
    0.50
    ir
    0.50
    Activations Density 0.062%

    No Known Activations