© 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. 70173
    Prev
    Next
    INDEX
    Explanations

    shouldn't followed by verb

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

    The neuron fires on the contraction suffix “’t” (as in don’t, shouldn’t, isn’t, 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_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
    骘
    -2.95
    戆
    -2.59
    颙
    -2.59
    텃
    -2.52
     cápsulas
    -2.52
    ÁCT
    -2.50
    ⽥
    -2.45
     海岸
    -2.44
    BIÉN
    -2.44
     馆
    -2.42
    POSITIVE LOGITS
    an
    4.34
    <i>
    3.27
    er
    3.19
    Y
    3.19
    to
    3.13
    "
    3.06
     
    2.97
    al
    2.94
    us
    2.86
    .
    2.83
    Activations Density 0.003%

    No Known Activations