© 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. 119425
    Prev
    Next
    INDEX
    Explanations

    character ASCII codes

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

    numeric literals in code, particularly single-digit numbers and ASCII character codes.

    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
    筴
    -1.55
    哢
    -1.45
    쐈
    -1.38
    吃了
    -1.34
    呿
    -1.30
     hätte
    -1.29
     wäre
    -1.26
     jambe
    -1.25
    <bos>
    -1.24
     eds
    -1.24
    POSITIVE LOGITS
     =
    1.44
     únicamente
    1.44
     or
    1.36
    0
    1.31
     algunas
    1.30
    涠
    1.29
    IANGLES
    1.29
     vorigen
    1.28
     +
    1.26
    もしくは
    1.26
    Activations Density 0.017%

    No Known Activations