© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101270
    Prev
    Next
    INDEX
    Explanations

    link rel href

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

    HTML link and meta tags in document headers.

    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
    磲
    -1.91
     its
    -1.70
    用手
    -1.70
    訁
    -1.62
    瑰
    -1.58
    はもう
    -1.57
    癀
    -1.55
    癭
    -1.55
     continually
    -1.55
    異常
    -1.55
    POSITIVE LOGITS
     on
    1.71
    e
    1.46
     слід
    1.45
    是個
    1.42
    quelize
    1.38
    řad
    1.38
     wtf
    1.36
     belakang
    1.34
     奶油
    1.34
    時的
    1.30
    Activations Density 0.019%

    No Known Activations