© 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. 9936
    Prev
    Next
    INDEX
    Explanations

    Kna-, Lili-, Chaudh-, microtub-, EW, cephal-

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

    scientific terminology and proper nouns in academic or technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron fires on the internal stems of long scientific or technical terms (e.g. fragments like “Lili–” in Liliaceae, “microtub–” in microtubule, “Kna–” in Knaresborough), effectively detecting the beginnings of specialized terminology.

    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
    .
    -2.66
    en
    -2.61
     '
    -2.53
    ه
    -2.47
    Now
    -2.47
    —
    -2.45
    The
    -2.44
    н
    -2.41
    नलोड
    -2.38
    L
    -2.38
    POSITIVE LOGITS
    屨
    2.67
    踽
    2.39
     санкт
    2.39
    啬
    2.34
    慫
    2.33
    〬
    2.33
    felpa
    2.33
    ꔹ
    2.28
     ň
    2.28
     sebagainya
    2.28
    Activations Density 0.047%

    No Known Activations