© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 50085
    Prev
    Next
    INDEX
    Explanations

    substrate, target, template, seed, probe

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

    scientific terms related to biological substrates, targets, and templates in research contexts.

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

    The neuron responds to technical molecular‐biology experimental component nouns.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    pherds
    -0.96
    llac
    -0.94
     récente
    -0.93
    alers
    -0.93
    finals
    -0.91
    deln
    -0.91
    мак
    -0.89
    coltura
    -0.87
    ḿ
    -0.86
    क्
    -0.85
    POSITIVE LOGITS
    となる
    1.41
     molecule
    1.20
     materials
    1.06
     berupa
    1.02
     candidates
    1.02
     material
    1.00
     molecules
    0.97
     countries
    0.94
     provided
    0.91
     organisms
    0.89
    Activations Density 0.308%

    No Known Activations