© 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. 74613
    Prev
    Next
    INDEX
    Explanations

    Rostov, pulsates, brood, hypocholesterolemic

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

    The neuron primarily detects biological/physiological processes, especially related to reproduction, pulsation, and biological rhythms in organisms.

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

    This neuron strongly responds to long, uncommon subword “stems” (e.g. single subword units like Rost, puls, brood etc.) rather than common short tokens.

    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
    
    -2.78
    ｿ
    -2.64
    耷
    -2.52
     Allgemeinen
    -2.52
    がありますが
    -2.42
    睥
    -2.42
     jenen
    -2.38
    関わ
    -2.36
     césped
    -2.34
    lentes
    -2.34
    POSITIVE LOGITS
    or
    4.44
    “
    3.91
    s
    3.25
    He
    3.17
    ter
    2.92
    And
    2.88
    n
    2.83
    </h1>
    2.81
    ta
    2.80
    「
    2.78
    Activations Density 0.031%

    No Known Activations