© 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. 34-GEMMASCOPE-RES-131K
    7. 97750
    Prev
    Next
    INDEX
    Explanations

    no longer

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

    The neuron specializes in detecting occurrences of the phrase “no longer.”

    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
     deklar
    -1.44
     already
    -1.39
     eventually
    -1.38
     dieß
    -1.32
     konstruk
    -1.32
     eléct
    -1.31
     konkret
    -1.30
    already
    -1.29
     駅前
    -1.28
     transak
    -1.28
    POSITIVE LOGITS
     anymore
    1.86
     any
    1.62
    有任何
    1.54
     in
    1.46
     as
    1.33
     Even
    1.31
    Even
    1.30
     need
    1.25
     than
    1.24
     even
    1.23
    Activations Density 0.023%

    No Known Activations