© 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. 34-GEMMASCOPE-RES-131K
    7. 91717
    Prev
    Next
    INDEX
    Explanations

    not sure what to expect

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

    This neuron detects negation markers, particularly occurrences of “not” or the contracted “n’t.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    setObject
    -0.95
    currently
    -0.94
    ícias
    -0.93
    ībā
    -0.90
    havn
    -0.89
     also
    -0.86
    UCHAR
    -0.86
    ånga
    -0.86
    ∙
    -0.84
     now
    -0.84
    POSITIVE LOGITS
     expecting
    2.08
     expect
    1.98
     expected
    1.92
     planned
    1.91
     expectation
    1.84
     expectations
    1.80
     knew
    1.73
     Expect
    1.66
    expect
    1.51
     expects
    1.50
    Activations Density 0.028%

    No Known Activations