© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127624
    Prev
    Next
    INDEX
    Explanations

    how much

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

    The neuron strongly activates on the phrase “how much,” i.e. quantifier constructions expressing “how much” of something.

    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
     Another
    -2.02
    The
    -1.90
     for
    -1.89
     These
    -1.88
     While
    -1.73
     Currently
    -1.73
     Because
    -1.70
     as
    -1.66
     Then
    -1.66
     Also
    -1.66
    POSITIVE LOGITS
    ビックリ
    1.99
    うーん
    1.99
    ほら
    1.80
    沨
    1.80
    และ
    1.76
    すっ
    1.76
    あぁ
    1.73
     और
    1.73
    きち
    1.71
    真ん
    1.69
    Activations Density 0.004%

    No Known Activations