© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83974
    Prev
    Next
    INDEX
    Explanations

    not [state word]

    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_34/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
     not
    -1.50
     and
    -1.46
     both
    -1.41
     without
    -1.17
     không
    -1.16
     nicht
    -1.13
     nothing
    -1.04
    ването
    -1.03
    にならない
    -1.02
     bukan
    -1.00
    POSITIVE LOGITS
     nor
    3.09
    nor
    2.28
    Nor
    1.90
    而是
    1.77
     sondern
    1.77
    either
    1.69
     Nor
    1.64
     either
    1.64
     anymore
    1.61
     tampoco
    1.58
    Activations Density 0.071%

    No Known Activations