© 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. 8917
    Prev
    Next
    INDEX
    Explanations

    Vaughan, SGD, AUD, Vita

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

    The neuron fires on rare or domain‐specific named entities—proper nouns, brand names, or other unique identifiers.

    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
    ?’
    -3.08
    忉
    -3.03
    瑨
    -2.98
    !’
    -2.92
    欉
    -2.89
    ﱠ
    -2.88
    锜
    -2.86
    銪
    -2.84
    ,’
    -2.83
    )’
    -2.80
    POSITIVE LOGITS
    _
    3.48
     '
    3.36
    [
    3.03
    '
    2.80
    –
    2.56
    鼉
    2.53
    ,
    2.47
     ``
    2.44
    ...
    2.42
    :
    2.39
    Activations Density 0.006%

    No Known Activations