© 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. 119062
    Prev
    Next
    INDEX
    Explanations

    meso-

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

    scientific terminology related to "meso-" prefixed chemical compounds and structures.

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

    The neuron activates on occurrences of the prefix “meso” (e.g. in words like mesophase, mesoporous, meso-substituted).

    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
    雠
    -2.33
    涠
    -2.27
     髪型
    -2.20
    旆
    -2.20
    啣
    -2.16
     sélectionner
    -2.11
     tomando
    -2.06
     gestartet
    -2.05
     obtenidos
    -2.02
     gekommen
    -2.00
    POSITIVE LOGITS
    i
    2.47
     \
    2.33
     ,
    2.16
     Ironically
    2.13
     //
    2.11
    、
    2.06
    Однако
    1.99
     Extremely
    1.98
     Addressing
    1.98
     लेकिन
    1.96
    Activations Density 0.015%

    No Known Activations