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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12744
    Prev
    Next
    INDEX
    Explanations

    returns null or false

    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
    又能
    -1.06
    蹿
    -1.05
    にある
    -1.05
     سپس
    -1.05
     then
    -1.04
    ennom
    -1.02
    <>
    -1.02
    titur
    -1.02
    =,
    -1.02
    assium
    -1.00
    POSITIVE LOGITS
     नहीं
    1.44
     none
    1.40
     null
    1.34
     not
    1.29
     no
    1.17
     nothing
    1.07
    NONE
    1.05
     NULL
    1.02
     hiçbir
    0.96
    ไม่มี
    0.94
    Activations Density 0.001%

    No Known Activations