© 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. 101458
    Prev
    Next
    INDEX
    Explanations

    jelly and gelatin

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

    This neuron detects the word "jelly" and related terms like "gelatin" and "jellies".

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

    This neuron activates on mentions of “jelly” (and related forms like “gelatinous”), i.e. tokens containing the “jel”/“gelat” sequence.

    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
    ↵
    -3.25
     quintessential
    -2.80
    V
    -2.73
     "
    -2.70
     alluring
    -2.69
    en
    -2.56
     mesmerizing
    -2.55
    迓
    -2.55
     enriching
    -2.50
    L
    -2.50
    POSITIVE LOGITS
    葙
    2.94
     respecting
    2.58
    ቷ
    2.55
     pernikahan
    2.39
    because
    2.38
    »:
    2.31
    ၜ
    2.30
    <bos>
    2.28
     because
    2.27
    といふ
    2.22
    Activations Density 0.003%

    No Known Activations