© 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. 10-GEMMASCOPE-RES-131K
    4. 61429
    Prev
    Next
    INDEX
    Explanations

    phosph- followed by suffixes

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

    chemical terms containing "phosph" prefix such as phosphor, phosphorous, and phosphene.

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

    The neuron activates on chemical terms containing the “phosph-” prefix (i.e. phosphorus-related compounds).

    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
    </b>
    -3.09
     הם
    -2.48
    縯
    -2.20
     inimigos
    -2.19
    贗
    -2.13
     funcionalidad
    -2.09
     Einladung
    -2.06
    such
    -2.06
     poby
    -2.05
     elaboración
    -2.00
    POSITIVE LOGITS
    </strong>
    3.72
    </h3>
    3.39
    y
    2.44
    ’
    2.41
     It
    2.38
     This
    2.31
    Rather
    2.31
     aktive
    2.31
     /
    2.27
     
    2.20
    Activations Density 0.013%

    No Known Activations