© 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. 99641
    Prev
    Next
    INDEX
    Explanations

    too many

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

    The neuron activates on instances of the phrasing “too many,” i.e. expressions of an excessive quantity.

    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
    h
    -1.73
    ”
    -1.72
    )
    -1.68
    –
    -1.67
    J
    -1.67
     was
    -1.63
    |
    -1.55
    L
    -1.54
    t
    -1.54
     can
    -1.54
    POSITIVE LOGITS
     otros
    1.44
     Dingen
    1.43
     ſame
    1.43
     ilustracja
    1.38
     habló
    1.38
     idiomas
    1.37
     projekty
    1.37
    ВОД
    1.36
     mencionó
    1.36
    在我的
    1.35
    Activations Density 0.010%

    No Known Activations