© 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. 22-GEMMASCOPE-RES-131K
    7. 71055
    Prev
    Next
    INDEX
    Explanations

    parsing strings and objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    kende
    -1.04
    ğim
    -0.91
    itoa
    -0.88
    只
    -0.88
     只
    -0.82
    ༼
    -0.81
     mostr
    -0.81
    ۱۳
    -0.81
     herald
    -0.81
    ॥
    -0.79
    POSITIVE LOGITS
    FromString
    1.23
     parse
    1.10
     from
    0.96
    parse
    0.91
     尔
    0.91
    ByName
    0.90
     by
    0.88
    Поэтому
    0.87
    恥ず
    0.84
    tersebut
    0.84
    Activations Density 0.062%

    No Known Activations