© 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. 22-GEMMASCOPE-RES-131K
    7. 68611
    Prev
    Next
    INDEX
    Explanations

    microRNAs and gene expression

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

    microRNA (miR) mentions in scientific literature.

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

    The neuron is highly sensitive to alphanumeric identifiers composed of letters and digits—especially microRNA (miR) labels and similar gene or sequence IDs.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     crumbling
    -1.26
     behauptet
    -1.19
     invece
    -1.10
    ⤒
    -1.09
     >
    -1.07
     although
    -1.06
    Préparation
    -1.06
     tireless
    -1.05
    WTS
    -1.05
    ера
    -1.05
    POSITIVE LOGITS
     that
    1.52
    咂
    1.34
     navnet
    1.22
    РЫ
    1.21
    rás
    1.19
     roligt
    1.12
     maanden
    1.09
     targeting
    1.09
    ât
    1.07
    deckung
    1.05
    Activations Density 0.062%

    No Known Activations