© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30541
    Prev
    Next
    INDEX
    Explanations

    quantity and multiplicity

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

    The neuron fires on words that express quantity or amount (e.g. several, many, multiple, all, etc.).

    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
     hvilke
    -1.20
     dwóch
    -1.11
     interessantes
    -1.10
    狁
    -1.09
    IMDb
    -1.09
    GOOGLE
    -1.09
     două
    -1.09
     ekolog
    -1.09
    䨻
    -1.08
    奩
    -1.08
    POSITIVE LOGITS
     item
    1.42
     thing
    1.06
     occasion
    1.05
     közül
    1.02
     we
    0.99
    h
    0.99
     option
    0.98
    ting
    0.94
     after
    0.90
    in
    0.90
    Activations Density 0.015%

    No Known Activations