© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10155
    Prev
    Next
    INDEX
    Explanations

    closing parentheses and brackets

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

    closing parentheses in coordinate pairs or array/list elements, particularly in technical or programming contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    傒
    -1.79
    悽
    -1.79
    Ꮉ
    -1.74
    齎
    -1.71
    峮
    -1.70
    来週
    -1.69
    𖣘
    -1.64
    几人
    -1.64
    rlpool
    -1.63
    　　「
    -1.61
    POSITIVE LOGITS
    d
    1.55
     '
    1.52
     are
    1.43
    尤其
    1.40
    al
    1.40
     får
    1.34
     pido
    1.31
    '.
    1.30
     hice
    1.30
    de
    1.30
    Activations Density 0.035%

    No Known Activations