© 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. 10515
    Prev
    Next
    INDEX
    Explanations

    scripting languages

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

    the word "script" or variations of it (especially when part of programming language names or technical terms).

    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
     одной
    -2.06
    神情
    -2.03
     resounding
    -2.02
    eſ
    -2.02
     distinto
    -1.97
    餬
    -1.95
    richlet
    -1.94
     connue
    -1.93
    だが
    -1.92
    ⟣
    -1.91
    POSITIVE LOGITS
    ↵
    2.83
    '
    2.41
    3
    2.39
    ’
    2.31
    .”
    2.28
     menschliche
    2.28
    4
    2.22
    y
    2.22
    ,"
    2.19
     giocatore
    2.13
    Activations Density 0.010%

    No Known Activations