© 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. 98311
    Prev
    Next
    INDEX
    Explanations

    anti-body monoclonal

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

    scientific research methods using antibodies for detection in immunological experiments.

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

    The neuron activates on technical immunology reagent terms, especially “anti-” and “immuno-” prefixes and antibody descriptors (e.g. monoclonal, polyclonal, rabbit antibody).

    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
    ,
    -1.27
     influence
    -1.09
     nawet
    -1.08
     любого
    -1.08
    uš
    -1.07
    ↵
    -1.07
    ⎧
    -1.05
     правительства
    -1.04
     السياس
    -1.02
     fluid
    -1.02
    POSITIVE LOGITS
     amerik
    1.20
    Mitä
    1.11
    ֶּ
    1.08
     soigneusement
    1.06
     used
    1.05
    Noten
    1.04
     qed
    1.03
    minated
    1.03
     vā
    1.02
     vinci
    1.00
    Activations Density 0.113%

    No Known Activations