© 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. 102972
    Prev
    Next
    INDEX
    Explanations

    Objective-C interface and Foundation classes

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

    opening square brackets in code that start method calls or array/object initializations.

    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
    n
    -1.84
     для
    -1.77
     untapped
    -1.63
     için
    -1.62
    这里是
    -1.61
    春季
    -1.60
     omin
    -1.59
    困惑
    -1.56
    ながらも
    -1.55
    ネギ
    -1.55
    POSITIVE LOGITS
     this
    2.50
     senjata
    1.76
     women
    1.74
     you
    1.70
    gucig
    1.66
     lavoratori
    1.63
     it
    1.63
     the
    1.59
     our
    1.59
    甞
    1.57
    Activations Density 0.005%

    No Known Activations