© 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. 1275
    Prev
    Next
    INDEX
    Explanations

    being and becoming

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

    The neuron selectively fires on unusually long, multi-syllable content tokens (e.g. technical terms, full names, and other lengthy words).

    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
     will
    -2.27
     would
    -2.08
     with
    -2.05
     when
    -1.92
     may
    -1.83
     might
    -1.83
     should
    -1.80
     can
    -1.77
     cannot
    -1.72
     that
    -1.70
    POSITIVE LOGITS
     being
    3.42
    being
    2.47
     becoming
    2.30
     having
    2.17
     étant
    2.13
    becoming
    1.88
    having
    1.86
     appearing
    1.74
     BEING
    1.72
     להיות
    1.70
    Activations Density 0.146%

    No Known Activations