© 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. 10-GEMMASCOPE-RES-131K
    7. 60412
    Prev
    Next
    INDEX
    Explanations

    too [adjective]

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

    The neuron essentially detects the adverb “too,” i.e. the intensifier “too” in the text.

    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
    on
    -2.64
    8
    -2.41
    a
    -2.36
    1
    -2.30
    3
    -2.23
    n
    -2.22
    鲧
    -2.20
    赑
    -2.20
    6
    -2.17
    the
    -2.16
    POSITIVE LOGITS
    熾
    2.09
    したり
    1.99
     ocasiones
    1.93
     exquisite
    1.89
    鏖
    1.85
    逹
    1.84
     große
    1.81
    </h1>
    1.80
     ingrained
    1.80
     exquisitely
    1.79
    Activations Density 0.007%

    No Known Activations