© 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. 48406
    Prev
    Next
    INDEX
    Explanations

    suprapontine, Leontini,ontouch

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

    The neuron consistently responds to the three‐letter sequence “ont” wherever it appears 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
    this
    -3.05
    archiwizowane
    -2.64
     hvil
    -2.58
    adakan
    -2.45
    ે
    -2.44
    臵
    -2.41
    嗞
    -2.41
     egens
    -2.33
     Có
    -2.30
    なみ
    -2.27
    POSITIVE LOGITS
    t
    4.03
    (
    3.53
    ont
    3.00
    —
    2.98
    –
    2.88
    n
    2.64
    en
    2.55
    т
    2.53
     abhor
    2.27
    刧
    2.25
    Activations Density 0.005%

    No Known Activations