© 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. 10-GEMMASCOPE-RES-131K
    7. 123493
    Prev
    Next
    INDEX
    Explanations

    tons of

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

    The neuron fires on the colloquial quantifier “tons of,” i.e. informal expressions of a large amount.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    褙
    -2.03
     wirklich
    -1.95
    ↵↵
    -1.88
    棪
    -1.86
    愀
    -1.84
     -}
    -1.84
     排骨
    -1.84
    ჻
    -1.83
    ᎒
    -1.81
     almofada
    -1.78
    POSITIVE LOGITS
    );
    2.03
     of
    1.89
    </strong>
    1.88
     is
    1.83
     was
    1.77
    ),
    1.68
     (>
    1.63
    就直接
    1.60
    ’,
    1.60
    ,'
    1.59
    Activations Density 0.009%

    No Known Activations