© 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. 29112
    Prev
    Next
    INDEX
    Explanations

    elongated shapes and descriptions

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

    The neuron fires most strongly on unusual single tokens—especially capitalized proper names (e.g. “Zara,” “Amelia”) or otherwise rare/distinctive words.

    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
    樒
    -2.84
    pecabe
    -2.84
    縢
    -2.81
    <bos>
    -2.72
    좆
    -2.64
    栁
    -2.64
    寕
    -2.64
    hmigung
    -2.63
    ꜄
    -2.59
    ̣i
    -2.58
    POSITIVE LOGITS
    ’
    4.44
    1
    3.27
    ’,
    3.19
    In
    2.98
    —
    2.86
    開始
    2.80
    …
    2.75
     the
    2.69
    2
    2.69
    <
    2.66
    Activations Density 0.007%

    No Known Activations