© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 103719
    Prev
    Next
    INDEX
    Explanations

    larval stages and claws

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

    biological structures like capsids, virions, flagella, larvae, and other anatomical parts of organisms.

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

    The neuron consistently activates on technical terms naming viral structural components—especially capsid, envelope, virion, and related proteins.

    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
     as
    -1.24
    }_{
    -1.15
     буквально
    -1.12
    dropIfExists
    -1.09
     eser
    -1.09
    čník
    -1.04
    WriteBarrier
    -1.02
    лювання
    -0.98
    Таким
    -0.98
    visation
    -0.98
    POSITIVE LOGITS
     estos
    1.26
    蚂蚁
    1.24
     woda
    1.22
     they
    1.17
     muß
    1.16
     spoko
    1.16
     Dicht
    1.16
    рия
    1.16
     Projektu
    1.15
     policiais
    1.14
    Activations Density 1.847%

    No Known Activations