© 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. 34684
    Prev
    Next
    INDEX
    Explanations

    conditional logic with null checks

    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
    ztes
    -1.12
     Inoltre
    -1.08
    deira
    -1.07
    Whereas
    -1.07
    焼く
    -1.01
     ヴィンテージ
    -0.99
    isier
    -0.98
    <bos>
    -0.97
    ckeye
    -0.97
    瑣
    -0.97
    POSITIVE LOGITS
     not
    1.07
     none
    1.07
     null
    1.06
     no
    0.96
    殃
    0.94
     mochilas
    0.93
     tantas
    0.92
     atractivo
    0.92
    kaos
    0.91
     Fläche
    0.90
    Activations Density 0.002%

    No Known Activations