© 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. 2251
    Prev
    Next
    INDEX
    Explanations

    array item properties, file access, code logic

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

    Calculate the specified

    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
    >∕
    0.43
    WILLIAM
    0.41
    芩
    0.39
    \%).
    0.39
    糠
    0.38
    spacePad
    0.37
    poetrylovers
    0.36
    Collegamenti
    0.36
    HUN
    0.36
    孺
    0.36
    POSITIVE LOGITS
     tuple
    0.80
     =>
    0.73
     succesfully
    0.71
     input
    0.70
     array
    0.70
     user
    0.70
     string
    0.70
     ->
    0.68
     params
    0.68
     values
    0.66
    Activations Density 0.107%

    No Known Activations