© 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. 76851
    Prev
    Next
    INDEX
    Explanations

    excess amounts

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

    The neuron reliably fires on occurrences of the word “excess,” marking mentions of surplus or overabundance.

    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
     metade
    -0.94
     kien
    -0.93
    outs
    -0.91
    adresse
    -0.88
    足够
    -0.88
     Podcasts
    -0.87
     effects
    -0.85
     カード
    -0.84
    рованы
    -0.84
    toi
    -0.84
    POSITIVE LOGITS
     of
    1.23
     Excess
    1.15
    Excess
    1.14
     baggage
    1.05
     excess
    0.97
     annuel
    0.92
     calories
    0.90
     jika
    0.90
     лук
    0.90
     geldi
    0.88
    Activations Density 0.012%

    No Known Activations